upload

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-366/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+base_model: models/DeepSeek-R1-Distill-Qwen-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/DeepSeek-R1-Distill-Qwen-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d953bcecd11620229236245187a31cde5d30d3fb85b1840f178c0b74d166e0
+size 161496088

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models/DeepSeek-R1-Distill-Qwen-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/DeepSeek-R1-Distill-Qwen-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7014791307bd91a5eabacc3e8706f81169f51151c1a25ebf2e08b6262352bf77
+size 161496088

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{%- if messages|length == 1 and messages[0]['role'] == 'assistant' -%}{%- if messages[0]['content'] is not none -%}{{'<｜Assistant｜>' + messages[0]['content'] + '<｜end▁of▁sentence｜>'}}{%- endif -%}{%- else -%}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{{'<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor -%}{%- endif -%}{% if add_generation_prompt %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5460750853242321,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027303754266211604,
+      "grad_norm": 3.856764554977417,
+      "learning_rate": 9.999815806238551e-06,
+      "loss": 0.5425,
+      "step": 1
+    },
+    {
+      "epoch": 0.005460750853242321,
+      "grad_norm": 3.6394715309143066,
+      "learning_rate": 9.999263238525135e-06,
+      "loss": 0.5588,
+      "step": 2
+    },
+    {
+      "epoch": 0.008191126279863481,
+      "grad_norm": 3.228754758834839,
+      "learning_rate": 9.998342337571566e-06,
+      "loss": 0.5072,
+      "step": 3
+    },
+    {
+      "epoch": 0.010921501706484642,
+      "grad_norm": 2.7734687328338623,
+      "learning_rate": 9.997053171227527e-06,
+      "loss": 0.524,
+      "step": 4
+    },
+    {
+      "epoch": 0.013651877133105802,
+      "grad_norm": 2.6146395206451416,
+      "learning_rate": 9.995395834475578e-06,
+      "loss": 0.5013,
+      "step": 5
+    },
+    {
+      "epoch": 0.016382252559726963,
+      "grad_norm": 2.3134093284606934,
+      "learning_rate": 9.993370449424153e-06,
+      "loss": 0.5021,
+      "step": 6
+    },
+    {
+      "epoch": 0.01911262798634812,
+      "grad_norm": 2.46028995513916,
+      "learning_rate": 9.990977165298571e-06,
+      "loss": 0.5048,
+      "step": 7
+    },
+    {
+      "epoch": 0.021843003412969283,
+      "grad_norm": 2.1209499835968018,
+      "learning_rate": 9.988216158430033e-06,
+      "loss": 0.4865,
+      "step": 8
+    },
+    {
+      "epoch": 0.024573378839590442,
+      "grad_norm": 2.0378663539886475,
+      "learning_rate": 9.985087632242634e-06,
+      "loss": 0.5033,
+      "step": 9
+    },
+    {
+      "epoch": 0.027303754266211604,
+      "grad_norm": 1.8533931970596313,
+      "learning_rate": 9.981591817238379e-06,
+      "loss": 0.4731,
+      "step": 10
+    },
+    {
+      "epoch": 0.030034129692832763,
+      "grad_norm": 1.7073378562927246,
+      "learning_rate": 9.977728970980193e-06,
+      "loss": 0.4592,
+      "step": 11
+    },
+    {
+      "epoch": 0.032764505119453925,
+      "grad_norm": 1.763203501701355,
+      "learning_rate": 9.973499378072947e-06,
+      "loss": 0.4569,
+      "step": 12
+    },
+    {
+      "epoch": 0.03549488054607509,
+      "grad_norm": 1.2629003524780273,
+      "learning_rate": 9.968903350142494e-06,
+      "loss": 0.4364,
+      "step": 13
+    },
+    {
+      "epoch": 0.03822525597269624,
+      "grad_norm": 1.345859408378601,
+      "learning_rate": 9.9639412258127e-06,
+      "loss": 0.4737,
+      "step": 14
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 1.291548490524292,
+      "learning_rate": 9.958613370680507e-06,
+      "loss": 0.4504,
+      "step": 15
+    },
+    {
+      "epoch": 0.04368600682593857,
+      "grad_norm": 1.3444461822509766,
+      "learning_rate": 9.952920177288985e-06,
+      "loss": 0.457,
+      "step": 16
+    },
+    {
+      "epoch": 0.04641638225255973,
+      "grad_norm": 1.5857586860656738,
+      "learning_rate": 9.946862065098415e-06,
+      "loss": 0.4696,
+      "step": 17
+    },
+    {
+      "epoch": 0.049146757679180884,
+      "grad_norm": 1.1109745502471924,
+      "learning_rate": 9.940439480455386e-06,
+      "loss": 0.4417,
+      "step": 18
+    },
+    {
+      "epoch": 0.05187713310580205,
+      "grad_norm": 1.1297810077667236,
+      "learning_rate": 9.933652896559907e-06,
+      "loss": 0.4463,
+      "step": 19
+    },
+    {
+      "epoch": 0.05460750853242321,
+      "grad_norm": 1.0981742143630981,
+      "learning_rate": 9.926502813430545e-06,
+      "loss": 0.4499,
+      "step": 20
+    },
+    {
+      "epoch": 0.05733788395904437,
+      "grad_norm": 1.1592185497283936,
+      "learning_rate": 9.918989757867584e-06,
+      "loss": 0.447,
+      "step": 21
+    },
+    {
+      "epoch": 0.060068259385665526,
+      "grad_norm": 1.0812605619430542,
+      "learning_rate": 9.911114283414204e-06,
+      "loss": 0.4638,
+      "step": 22
+    },
+    {
+      "epoch": 0.06279863481228669,
+      "grad_norm": 0.774226188659668,
+      "learning_rate": 9.902876970315715e-06,
+      "loss": 0.4439,
+      "step": 23
+    },
+    {
+      "epoch": 0.06552901023890785,
+      "grad_norm": 0.7117806673049927,
+      "learning_rate": 9.89427842547679e-06,
+      "loss": 0.4424,
+      "step": 24
+    },
+    {
+      "epoch": 0.06825938566552901,
+      "grad_norm": 0.7732372283935547,
+      "learning_rate": 9.885319282416755e-06,
+      "loss": 0.4494,
+      "step": 25
+    },
+    {
+      "epoch": 0.07098976109215017,
+      "grad_norm": 0.7167857885360718,
+      "learning_rate": 9.876000201222912e-06,
+      "loss": 0.4514,
+      "step": 26
+    },
+    {
+      "epoch": 0.07372013651877134,
+      "grad_norm": 0.7761046290397644,
+      "learning_rate": 9.866321868501914e-06,
+      "loss": 0.462,
+      "step": 27
+    },
+    {
+      "epoch": 0.07645051194539249,
+      "grad_norm": 0.5660157203674316,
+      "learning_rate": 9.856284997329158e-06,
+      "loss": 0.4455,
+      "step": 28
+    },
+    {
+      "epoch": 0.07918088737201365,
+      "grad_norm": 0.5861382484436035,
+      "learning_rate": 9.845890327196269e-06,
+      "loss": 0.4416,
+      "step": 29
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 0.7201432585716248,
+      "learning_rate": 9.835138623956603e-06,
+      "loss": 0.4209,
+      "step": 30
+    },
+    {
+      "epoch": 0.08464163822525597,
+      "grad_norm": 0.8803044557571411,
+      "learning_rate": 9.824030679768824e-06,
+      "loss": 0.4276,
+      "step": 31
+    },
+    {
+      "epoch": 0.08737201365187713,
+      "grad_norm": 0.7925510406494141,
+      "learning_rate": 9.812567313038542e-06,
+      "loss": 0.4473,
+      "step": 32
+    },
+    {
+      "epoch": 0.0901023890784983,
+      "grad_norm": 0.9926882982254028,
+      "learning_rate": 9.80074936835801e-06,
+      "loss": 0.4398,
+      "step": 33
+    },
+    {
+      "epoch": 0.09283276450511946,
+      "grad_norm": 0.8362368941307068,
+      "learning_rate": 9.788577716443903e-06,
+      "loss": 0.4347,
+      "step": 34
+    },
+    {
+      "epoch": 0.09556313993174062,
+      "grad_norm": 0.8301376104354858,
+      "learning_rate": 9.77605325407316e-06,
+      "loss": 0.4684,
+      "step": 35
+    },
+    {
+      "epoch": 0.09829351535836177,
+      "grad_norm": 0.7239497900009155,
+      "learning_rate": 9.763176904016914e-06,
+      "loss": 0.4686,
+      "step": 36
+    },
+    {
+      "epoch": 0.10102389078498293,
+      "grad_norm": 0.6108490824699402,
+      "learning_rate": 9.749949614972507e-06,
+      "loss": 0.431,
+      "step": 37
+    },
+    {
+      "epoch": 0.1037542662116041,
+      "grad_norm": 0.5505651235580444,
+      "learning_rate": 9.736372361493584e-06,
+      "loss": 0.4383,
+      "step": 38
+    },
+    {
+      "epoch": 0.10648464163822526,
+      "grad_norm": 0.5642620325088501,
+      "learning_rate": 9.722446143918307e-06,
+      "loss": 0.4249,
+      "step": 39
+    },
+    {
+      "epoch": 0.10921501706484642,
+      "grad_norm": 0.4733835458755493,
+      "learning_rate": 9.70817198829563e-06,
+      "loss": 0.4404,
+      "step": 40
+    },
+    {
+      "epoch": 0.11194539249146758,
+      "grad_norm": 0.43274644017219543,
+      "learning_rate": 9.693550946309721e-06,
+      "loss": 0.428,
+      "step": 41
+    },
+    {
+      "epoch": 0.11467576791808874,
+      "grad_norm": 0.45345625281333923,
+      "learning_rate": 9.678584095202468e-06,
+      "loss": 0.4559,
+      "step": 42
+    },
+    {
+      "epoch": 0.1174061433447099,
+      "grad_norm": 0.3903965353965759,
+      "learning_rate": 9.663272537694112e-06,
+      "loss": 0.4419,
+      "step": 43
+    },
+    {
+      "epoch": 0.12013651877133105,
+      "grad_norm": 0.5206829905509949,
+      "learning_rate": 9.647617401902003e-06,
+      "loss": 0.4366,
+      "step": 44
+    },
+    {
+      "epoch": 0.12286689419795221,
+      "grad_norm": 0.38311880826950073,
+      "learning_rate": 9.631619841257477e-06,
+      "loss": 0.4289,
+      "step": 45
+    },
+    {
+      "epoch": 0.12559726962457338,
+      "grad_norm": 0.4225156903266907,
+      "learning_rate": 9.615281034420882e-06,
+      "loss": 0.4215,
+      "step": 46
+    },
+    {
+      "epoch": 0.12832764505119454,
+      "grad_norm": 0.4255654513835907,
+      "learning_rate": 9.598602185194733e-06,
+      "loss": 0.4247,
+      "step": 47
+    },
+    {
+      "epoch": 0.1310580204778157,
+      "grad_norm": 0.4347112774848938,
+      "learning_rate": 9.581584522435025e-06,
+      "loss": 0.427,
+      "step": 48
+    },
+    {
+      "epoch": 0.13378839590443686,
+      "grad_norm": 0.34471118450164795,
+      "learning_rate": 9.564229299960679e-06,
+      "loss": 0.421,
+      "step": 49
+    },
+    {
+      "epoch": 0.13651877133105803,
+      "grad_norm": 0.43423381447792053,
+      "learning_rate": 9.54653779646118e-06,
+      "loss": 0.4322,
+      "step": 50
+    },
+    {
+      "epoch": 0.1392491467576792,
+      "grad_norm": 0.4541296064853668,
+      "learning_rate": 9.528511315402358e-06,
+      "loss": 0.4212,
+      "step": 51
+    },
+    {
+      "epoch": 0.14197952218430035,
+      "grad_norm": 0.29571640491485596,
+      "learning_rate": 9.510151184930354e-06,
+      "loss": 0.4312,
+      "step": 52
+    },
+    {
+      "epoch": 0.1447098976109215,
+      "grad_norm": 0.30192604660987854,
+      "learning_rate": 9.491458757773766e-06,
+      "loss": 0.4328,
+      "step": 53
+    },
+    {
+      "epoch": 0.14744027303754267,
+      "grad_norm": 0.24025903642177582,
+      "learning_rate": 9.472435411143979e-06,
+      "loss": 0.4214,
+      "step": 54
+    },
+    {
+      "epoch": 0.15017064846416384,
+      "grad_norm": 0.3551096022129059,
+      "learning_rate": 9.453082546633704e-06,
+      "loss": 0.4232,
+      "step": 55
+    },
+    {
+      "epoch": 0.15290102389078497,
+      "grad_norm": 0.2226678431034088,
+      "learning_rate": 9.433401590113702e-06,
+      "loss": 0.4332,
+      "step": 56
+    },
+    {
+      "epoch": 0.15563139931740613,
+      "grad_norm": 0.21858179569244385,
+      "learning_rate": 9.413393991627737e-06,
+      "loss": 0.418,
+      "step": 57
+    },
+    {
+      "epoch": 0.1583617747440273,
+      "grad_norm": 0.22533869743347168,
+      "learning_rate": 9.393061225285743e-06,
+      "loss": 0.4361,
+      "step": 58
+    },
+    {
+      "epoch": 0.16109215017064846,
+      "grad_norm": 0.21001799404621124,
+      "learning_rate": 9.372404789155199e-06,
+      "loss": 0.4187,
+      "step": 59
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.20293086767196655,
+      "learning_rate": 9.351426205150778e-06,
+      "loss": 0.4252,
+      "step": 60
+    },
+    {
+      "epoch": 0.16655290102389078,
+      "grad_norm": 0.22262097895145416,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.4442,
+      "step": 61
+    },
+    {
+      "epoch": 0.16928327645051194,
+      "grad_norm": 0.21581031382083893,
+      "learning_rate": 9.30850879974034e-06,
+      "loss": 0.4233,
+      "step": 62
+    },
+    {
+      "epoch": 0.1720136518771331,
+      "grad_norm": 0.2510773837566376,
+      "learning_rate": 9.286573140381663e-06,
+      "loss": 0.4126,
+      "step": 63
+    },
+    {
+      "epoch": 0.17474402730375427,
+      "grad_norm": 0.22764866054058075,
+      "learning_rate": 9.2643216570108e-06,
+      "loss": 0.4435,
+      "step": 64
+    },
+    {
+      "epoch": 0.17747440273037543,
+      "grad_norm": 0.2921380400657654,
+      "learning_rate": 9.24175598906152e-06,
+      "loss": 0.4006,
+      "step": 65
+    },
+    {
+      "epoch": 0.1802047781569966,
+      "grad_norm": 0.2642498314380646,
+      "learning_rate": 9.218877799115929e-06,
+      "loss": 0.4224,
+      "step": 66
+    },
+    {
+      "epoch": 0.18293515358361775,
+      "grad_norm": 0.2313549965620041,
+      "learning_rate": 9.19568877278197e-06,
+      "loss": 0.413,
+      "step": 67
+    },
+    {
+      "epoch": 0.18566552901023892,
+      "grad_norm": 0.2201680839061737,
+      "learning_rate": 9.172190618569236e-06,
+      "loss": 0.4278,
+      "step": 68
+    },
+    {
+      "epoch": 0.18839590443686008,
+      "grad_norm": 0.2556556463241577,
+      "learning_rate": 9.148385067763094e-06,
+      "loss": 0.4216,
+      "step": 69
+    },
+    {
+      "epoch": 0.19112627986348124,
+      "grad_norm": 0.238591730594635,
+      "learning_rate": 9.124273874297123e-06,
+      "loss": 0.4217,
+      "step": 70
+    },
+    {
+      "epoch": 0.19385665529010238,
+      "grad_norm": 0.2658149302005768,
+      "learning_rate": 9.099858814623887e-06,
+      "loss": 0.4159,
+      "step": 71
+    },
+    {
+      "epoch": 0.19658703071672354,
+      "grad_norm": 0.26856058835983276,
+      "learning_rate": 9.075141687584056e-06,
+      "loss": 0.4285,
+      "step": 72
+    },
+    {
+      "epoch": 0.1993174061433447,
+      "grad_norm": 0.1793709248304367,
+      "learning_rate": 9.050124314273876e-06,
+      "loss": 0.4255,
+      "step": 73
+    },
+    {
+      "epoch": 0.20204778156996586,
+      "grad_norm": 0.1868457794189453,
+      "learning_rate": 9.024808537910981e-06,
+      "loss": 0.417,
+      "step": 74
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.19721131026744843,
+      "learning_rate": 8.999196223698599e-06,
+      "loss": 0.4234,
+      "step": 75
+    },
+    {
+      "epoch": 0.2075085324232082,
+      "grad_norm": 0.1849862039089203,
+      "learning_rate": 8.973289258688125e-06,
+      "loss": 0.3868,
+      "step": 76
+    },
+    {
+      "epoch": 0.21023890784982935,
+      "grad_norm": 0.18427810072898865,
+      "learning_rate": 8.9470895516401e-06,
+      "loss": 0.4205,
+      "step": 77
+    },
+    {
+      "epoch": 0.2129692832764505,
+      "grad_norm": 0.22481605410575867,
+      "learning_rate": 8.920599032883553e-06,
+      "loss": 0.4271,
+      "step": 78
+    },
+    {
+      "epoch": 0.21569965870307167,
+      "grad_norm": 0.18275555968284607,
+      "learning_rate": 8.893819654173804e-06,
+      "loss": 0.4276,
+      "step": 79
+    },
+    {
+      "epoch": 0.21843003412969283,
+      "grad_norm": 0.17510327696800232,
+      "learning_rate": 8.86675338854865e-06,
+      "loss": 0.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.221160409556314,
+      "grad_norm": 0.18124502897262573,
+      "learning_rate": 8.839402230183e-06,
+      "loss": 0.4181,
+      "step": 81
+    },
+    {
+      "epoch": 0.22389078498293516,
+      "grad_norm": 0.1930208057165146,
+      "learning_rate": 8.811768194241951e-06,
+      "loss": 0.4326,
+      "step": 82
+    },
+    {
+      "epoch": 0.22662116040955632,
+      "grad_norm": 0.17881739139556885,
+      "learning_rate": 8.783853316732313e-06,
+      "loss": 0.4227,
+      "step": 83
+    },
+    {
+      "epoch": 0.22935153583617748,
+      "grad_norm": 0.18276868760585785,
+      "learning_rate": 8.755659654352599e-06,
+      "loss": 0.4109,
+      "step": 84
+    },
+    {
+      "epoch": 0.23208191126279865,
+      "grad_norm": 0.1769554764032364,
+      "learning_rate": 8.727189284341501e-06,
+      "loss": 0.4267,
+      "step": 85
+    },
+    {
+      "epoch": 0.2348122866894198,
+      "grad_norm": 0.22149443626403809,
+      "learning_rate": 8.698444304324837e-06,
+      "loss": 0.4236,
+      "step": 86
+    },
+    {
+      "epoch": 0.23754266211604094,
+      "grad_norm": 0.1817912608385086,
+      "learning_rate": 8.669426832160997e-06,
+      "loss": 0.4235,
+      "step": 87
+    },
+    {
+      "epoch": 0.2402730375426621,
+      "grad_norm": 0.23118089139461517,
+      "learning_rate": 8.640139005784924e-06,
+      "loss": 0.4338,
+      "step": 88
+    },
+    {
+      "epoch": 0.24300341296928327,
+      "grad_norm": 0.23663879930973053,
+      "learning_rate": 8.610582983050581e-06,
+      "loss": 0.4239,
+      "step": 89
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.16908958554267883,
+      "learning_rate": 8.580760941571968e-06,
+      "loss": 0.4148,
+      "step": 90
+    },
+    {
+      "epoch": 0.2484641638225256,
+      "grad_norm": 0.23422765731811523,
+      "learning_rate": 8.55067507856268e-06,
+      "loss": 0.4183,
+      "step": 91
+    },
+    {
+      "epoch": 0.25119453924914675,
+      "grad_norm": 0.24864593148231506,
+      "learning_rate": 8.520327610674029e-06,
+      "loss": 0.41,
+      "step": 92
+    },
+    {
+      "epoch": 0.25392491467576794,
+      "grad_norm": 0.20847055315971375,
+      "learning_rate": 8.489720773831717e-06,
+      "loss": 0.4221,
+      "step": 93
+    },
+    {
+      "epoch": 0.2566552901023891,
+      "grad_norm": 0.19055533409118652,
+      "learning_rate": 8.458856823071111e-06,
+      "loss": 0.4191,
+      "step": 94
+    },
+    {
+      "epoch": 0.2593856655290102,
+      "grad_norm": 0.24293097853660583,
+      "learning_rate": 8.427738032371078e-06,
+      "loss": 0.3906,
+      "step": 95
+    },
+    {
+      "epoch": 0.2621160409556314,
+      "grad_norm": 0.23974299430847168,
+      "learning_rate": 8.396366694486466e-06,
+      "loss": 0.4157,
+      "step": 96
+    },
+    {
+      "epoch": 0.26484641638225254,
+      "grad_norm": 0.1998283416032791,
+      "learning_rate": 8.364745120779166e-06,
+      "loss": 0.4054,
+      "step": 97
+    },
+    {
+      "epoch": 0.2675767918088737,
+      "grad_norm": 0.21701572835445404,
+      "learning_rate": 8.332875641047817e-06,
+      "loss": 0.3984,
+      "step": 98
+    },
+    {
+      "epoch": 0.27030716723549486,
+      "grad_norm": 0.18561778962612152,
+      "learning_rate": 8.30076060335616e-06,
+      "loss": 0.4164,
+      "step": 99
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 0.1797938048839569,
+      "learning_rate": 8.26840237386003e-06,
+      "loss": 0.4339,
+      "step": 100
+    },
+    {
+      "epoch": 0.2757679180887372,
+      "grad_norm": 0.1605861335992813,
+      "learning_rate": 8.235803336633033e-06,
+      "loss": 0.4053,
+      "step": 101
+    },
+    {
+      "epoch": 0.2784982935153584,
+      "grad_norm": 0.1774858683347702,
+      "learning_rate": 8.202965893490877e-06,
+      "loss": 0.4232,
+      "step": 102
+    },
+    {
+      "epoch": 0.2812286689419795,
+      "grad_norm": 0.15541759133338928,
+      "learning_rate": 8.169892463814435e-06,
+      "loss": 0.4208,
+      "step": 103
+    },
+    {
+      "epoch": 0.2839590443686007,
+      "grad_norm": 0.16066958010196686,
+      "learning_rate": 8.136585484371471e-06,
+      "loss": 0.4074,
+      "step": 104
+    },
+    {
+      "epoch": 0.28668941979522183,
+      "grad_norm": 0.1789342761039734,
+      "learning_rate": 8.103047409137114e-06,
+      "loss": 0.4104,
+      "step": 105
+    },
+    {
+      "epoch": 0.289419795221843,
+      "grad_norm": 0.16283057630062103,
+      "learning_rate": 8.06928070911306e-06,
+      "loss": 0.4073,
+      "step": 106
+    },
+    {
+      "epoch": 0.29215017064846416,
+      "grad_norm": 0.17041556537151337,
+      "learning_rate": 8.035287872145502e-06,
+      "loss": 0.4396,
+      "step": 107
+    },
+    {
+      "epoch": 0.29488054607508535,
+      "grad_norm": 0.17072531580924988,
+      "learning_rate": 8.001071402741843e-06,
+      "loss": 0.4297,
+      "step": 108
+    },
+    {
+      "epoch": 0.2976109215017065,
+      "grad_norm": 0.16717186570167542,
+      "learning_rate": 7.96663382188616e-06,
+      "loss": 0.408,
+      "step": 109
+    },
+    {
+      "epoch": 0.3003412969283277,
+      "grad_norm": 0.16995355486869812,
+      "learning_rate": 7.93197766685348e-06,
+      "loss": 0.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.3030716723549488,
+      "grad_norm": 0.1682933270931244,
+      "learning_rate": 7.897105491022819e-06,
+      "loss": 0.4179,
+      "step": 111
+    },
+    {
+      "epoch": 0.30580204778156994,
+      "grad_norm": 0.15432436764240265,
+      "learning_rate": 7.862019863689075e-06,
+      "loss": 0.4037,
+      "step": 112
+    },
+    {
+      "epoch": 0.30853242320819113,
+      "grad_norm": 0.16314339637756348,
+      "learning_rate": 7.826723369873715e-06,
+      "loss": 0.4066,
+      "step": 113
+    },
+    {
+      "epoch": 0.31126279863481227,
+      "grad_norm": 0.17164085805416107,
+      "learning_rate": 7.791218610134324e-06,
+      "loss": 0.4328,
+      "step": 114
+    },
+    {
+      "epoch": 0.31399317406143346,
+      "grad_norm": 0.16329169273376465,
+      "learning_rate": 7.755508200373e-06,
+      "loss": 0.41,
+      "step": 115
+    },
+    {
+      "epoch": 0.3167235494880546,
+      "grad_norm": 0.15500546991825104,
+      "learning_rate": 7.719594771643623e-06,
+      "loss": 0.4023,
+      "step": 116
+    },
+    {
+      "epoch": 0.3194539249146758,
+      "grad_norm": 0.16174261271953583,
+      "learning_rate": 7.683480969958005e-06,
+      "loss": 0.4147,
+      "step": 117
+    },
+    {
+      "epoch": 0.3221843003412969,
+      "grad_norm": 0.16179116070270538,
+      "learning_rate": 7.647169456090925e-06,
+      "loss": 0.4198,
+      "step": 118
+    },
+    {
+      "epoch": 0.3249146757679181,
+      "grad_norm": 0.1634499430656433,
+      "learning_rate": 7.6106629053841255e-06,
+      "loss": 0.4162,
+      "step": 119
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.17482595145702362,
+      "learning_rate": 7.5739640075491546e-06,
+      "loss": 0.4304,
+      "step": 120
+    },
+    {
+      "epoch": 0.33037542662116043,
+      "grad_norm": 0.16381986439228058,
+      "learning_rate": 7.537075466469228e-06,
+      "loss": 0.4076,
+      "step": 121
+    },
+    {
+      "epoch": 0.33310580204778156,
+      "grad_norm": 0.15148329734802246,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3943,
+      "step": 122
+    },
+    {
+      "epoch": 0.33583617747440275,
+      "grad_norm": 0.17150920629501343,
+      "learning_rate": 7.462740339769323e-06,
+      "loss": 0.4221,
+      "step": 123
+    },
+    {
+      "epoch": 0.3385665529010239,
+      "grad_norm": 0.16451485455036163,
+      "learning_rate": 7.425299230975982e-06,
+      "loss": 0.3909,
+      "step": 124
+    },
+    {
+      "epoch": 0.3412969283276451,
+      "grad_norm": 0.1635640561580658,
+      "learning_rate": 7.387679432187442e-06,
+      "loss": 0.412,
+      "step": 125
+    },
+    {
+      "epoch": 0.3440273037542662,
+      "grad_norm": 0.15344786643981934,
+      "learning_rate": 7.349883715136601e-06,
+      "loss": 0.3957,
+      "step": 126
+    },
+    {
+      "epoch": 0.34675767918088735,
+      "grad_norm": 0.20929256081581116,
+      "learning_rate": 7.311914864517575e-06,
+      "loss": 0.4172,
+      "step": 127
+    },
+    {
+      "epoch": 0.34948805460750854,
+      "grad_norm": 0.15553469955921173,
+      "learning_rate": 7.27377567778053e-06,
+      "loss": 0.4255,
+      "step": 128
+    },
+    {
+      "epoch": 0.35221843003412967,
+      "grad_norm": 0.16687364876270294,
+      "learning_rate": 7.235468964925571e-06,
+      "loss": 0.4032,
+      "step": 129
+    },
+    {
+      "epoch": 0.35494880546075086,
+      "grad_norm": 0.15902447700500488,
+      "learning_rate": 7.1969975482957075e-06,
+      "loss": 0.4264,
+      "step": 130
+    },
+    {
+      "epoch": 0.357679180887372,
+      "grad_norm": 0.16279031336307526,
+      "learning_rate": 7.158364262368919e-06,
+      "loss": 0.4081,
+      "step": 131
+    },
+    {
+      "epoch": 0.3604095563139932,
+      "grad_norm": 0.1744302660226822,
+      "learning_rate": 7.119571953549305e-06,
+      "loss": 0.4439,
+      "step": 132
+    },
+    {
+      "epoch": 0.3631399317406143,
+      "grad_norm": 0.16045725345611572,
+      "learning_rate": 7.080623479957372e-06,
+      "loss": 0.3996,
+      "step": 133
+    },
+    {
+      "epoch": 0.3658703071672355,
+      "grad_norm": 0.16313788294792175,
+      "learning_rate": 7.041521711219468e-06,
+      "loss": 0.4055,
+      "step": 134
+    },
+    {
+      "epoch": 0.36860068259385664,
+      "grad_norm": 0.15558135509490967,
+      "learning_rate": 7.002269528256334e-06,
+      "loss": 0.4074,
+      "step": 135
+    },
+    {
+      "epoch": 0.37133105802047783,
+      "grad_norm": 0.16284853219985962,
+      "learning_rate": 6.9628698230708604e-06,
+      "loss": 0.3937,
+      "step": 136
+    },
+    {
+      "epoch": 0.37406143344709897,
+      "grad_norm": 0.1701689511537552,
+      "learning_rate": 6.9233254985350066e-06,
+      "loss": 0.4014,
+      "step": 137
+    },
+    {
+      "epoch": 0.37679180887372016,
+      "grad_norm": 0.16153037548065186,
+      "learning_rate": 6.883639468175926e-06,
+      "loss": 0.4345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3795221843003413,
+      "grad_norm": 0.15898269414901733,
+      "learning_rate": 6.843814655961302e-06,
+      "loss": 0.4117,
+      "step": 139
+    },
+    {
+      "epoch": 0.3822525597269625,
+      "grad_norm": 0.15082918107509613,
+      "learning_rate": 6.803853996083918e-06,
+      "loss": 0.4041,
+      "step": 140
+    },
+    {
+      "epoch": 0.3849829351535836,
+      "grad_norm": 0.15225613117218018,
+      "learning_rate": 6.763760432745475e-06,
+      "loss": 0.4203,
+      "step": 141
+    },
+    {
+      "epoch": 0.38771331058020475,
+      "grad_norm": 0.15860538184642792,
+      "learning_rate": 6.723536919939669e-06,
+      "loss": 0.409,
+      "step": 142
+    },
+    {
+      "epoch": 0.39044368600682594,
+      "grad_norm": 0.15701624751091003,
+      "learning_rate": 6.683186421234552e-06,
+      "loss": 0.411,
+      "step": 143
+    },
+    {
+      "epoch": 0.3931740614334471,
+      "grad_norm": 0.1592189222574234,
+      "learning_rate": 6.6427119095541745e-06,
+      "loss": 0.4034,
+      "step": 144
+    },
+    {
+      "epoch": 0.39590443686006827,
+      "grad_norm": 0.16646814346313477,
+      "learning_rate": 6.602116366959556e-06,
+      "loss": 0.411,
+      "step": 145
+    },
+    {
+      "epoch": 0.3986348122866894,
+      "grad_norm": 0.16729459166526794,
+      "learning_rate": 6.561402784428974e-06,
+      "loss": 0.4032,
+      "step": 146
+    },
+    {
+      "epoch": 0.4013651877133106,
+      "grad_norm": 0.16820791363716125,
+      "learning_rate": 6.520574161637591e-06,
+      "loss": 0.4087,
+      "step": 147
+    },
+    {
+      "epoch": 0.4040955631399317,
+      "grad_norm": 0.17279136180877686,
+      "learning_rate": 6.479633506736447e-06,
+      "loss": 0.3949,
+      "step": 148
+    },
+    {
+      "epoch": 0.4068259385665529,
+      "grad_norm": 0.15827003121376038,
+      "learning_rate": 6.438583836130835e-06,
+      "loss": 0.4134,
+      "step": 149
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.3199061155319214,
+      "learning_rate": 6.397428174258048e-06,
+      "loss": 0.3956,
+      "step": 150
+    },
+    {
+      "epoch": 0.41228668941979524,
+      "grad_norm": 0.15721672773361206,
+      "learning_rate": 6.3561695533645505e-06,
+      "loss": 0.408,
+      "step": 151
+    },
+    {
+      "epoch": 0.4150170648464164,
+      "grad_norm": 0.16460402309894562,
+      "learning_rate": 6.314811013282574e-06,
+      "loss": 0.4083,
+      "step": 152
+    },
+    {
+      "epoch": 0.41774744027303756,
+      "grad_norm": 0.156940758228302,
+      "learning_rate": 6.273355601206143e-06,
+      "loss": 0.4062,
+      "step": 153
+    },
+    {
+      "epoch": 0.4204778156996587,
+      "grad_norm": 0.15688540041446686,
+      "learning_rate": 6.231806371466574e-06,
+      "loss": 0.4051,
+      "step": 154
+    },
+    {
+      "epoch": 0.4232081911262799,
+      "grad_norm": 0.14866897463798523,
+      "learning_rate": 6.190166385307428e-06,
+      "loss": 0.4047,
+      "step": 155
+    },
+    {
+      "epoch": 0.425938566552901,
+      "grad_norm": 0.15852367877960205,
+      "learning_rate": 6.148438710658979e-06,
+      "loss": 0.4043,
+      "step": 156
+    },
+    {
+      "epoch": 0.4286689419795222,
+      "grad_norm": 0.1479935199022293,
+      "learning_rate": 6.106626421912163e-06,
+      "loss": 0.4073,
+      "step": 157
+    },
+    {
+      "epoch": 0.43139931740614335,
+      "grad_norm": 0.1690177172422409,
+      "learning_rate": 6.064732599692079e-06,
+      "loss": 0.4148,
+      "step": 158
+    },
+    {
+      "epoch": 0.4341296928327645,
+      "grad_norm": 0.1765451729297638,
+      "learning_rate": 6.022760330631006e-06,
+      "loss": 0.4105,
+      "step": 159
+    },
+    {
+      "epoch": 0.43686006825938567,
+      "grad_norm": 0.16014869511127472,
+      "learning_rate": 5.980712707140985e-06,
+      "loss": 0.4138,
+      "step": 160
+    },
+    {
+      "epoch": 0.4395904436860068,
+      "grad_norm": 0.1788393259048462,
+      "learning_rate": 5.938592827185994e-06,
+      "loss": 0.4224,
+      "step": 161
+    },
+    {
+      "epoch": 0.442320819112628,
+      "grad_norm": 0.1551506668329239,
+      "learning_rate": 5.896403794053679e-06,
+      "loss": 0.4058,
+      "step": 162
+    },
+    {
+      "epoch": 0.44505119453924913,
+      "grad_norm": 0.1573813110589981,
+      "learning_rate": 5.854148716126722e-06,
+      "loss": 0.4147,
+      "step": 163
+    },
+    {
+      "epoch": 0.4477815699658703,
+      "grad_norm": 0.16244283318519592,
+      "learning_rate": 5.811830706653819e-06,
+      "loss": 0.4152,
+      "step": 164
+    },
+    {
+      "epoch": 0.45051194539249145,
+      "grad_norm": 0.17180225253105164,
+      "learning_rate": 5.76945288352031e-06,
+      "loss": 0.3972,
+      "step": 165
+    },
+    {
+      "epoch": 0.45324232081911264,
+      "grad_norm": 0.16414454579353333,
+      "learning_rate": 5.72701836901845e-06,
+      "loss": 0.403,
+      "step": 166
+    },
+    {
+      "epoch": 0.4559726962457338,
+      "grad_norm": 0.3096899092197418,
+      "learning_rate": 5.684530289617377e-06,
+      "loss": 0.4195,
+      "step": 167
+    },
+    {
+      "epoch": 0.45870307167235497,
+      "grad_norm": 0.16957193613052368,
+      "learning_rate": 5.641991775732756e-06,
+      "loss": 0.405,
+      "step": 168
+    },
+    {
+      "epoch": 0.4614334470989761,
+      "grad_norm": 0.16117002069950104,
+      "learning_rate": 5.599405961496137e-06,
+      "loss": 0.398,
+      "step": 169
+    },
+    {
+      "epoch": 0.4641638225255973,
+      "grad_norm": 0.17450742423534393,
+      "learning_rate": 5.556775984524044e-06,
+      "loss": 0.4009,
+      "step": 170
+    },
+    {
+      "epoch": 0.4668941979522184,
+      "grad_norm": 0.15785841643810272,
+      "learning_rate": 5.514104985686802e-06,
+      "loss": 0.3838,
+      "step": 171
+    },
+    {
+      "epoch": 0.4696245733788396,
+      "grad_norm": 0.22598251700401306,
+      "learning_rate": 5.471396108877123e-06,
+      "loss": 0.4176,
+      "step": 172
+    },
+    {
+      "epoch": 0.47235494880546075,
+      "grad_norm": 0.17126567661762238,
+      "learning_rate": 5.428652500778472e-06,
+      "loss": 0.4135,
+      "step": 173
+    },
+    {
+      "epoch": 0.4750853242320819,
+      "grad_norm": 0.1700679510831833,
+      "learning_rate": 5.385877310633233e-06,
+      "loss": 0.4259,
+      "step": 174
+    },
+    {
+      "epoch": 0.4778156996587031,
+      "grad_norm": 0.1624089628458023,
+      "learning_rate": 5.3430736900106715e-06,
+      "loss": 0.4425,
+      "step": 175
+    },
+    {
+      "epoch": 0.4805460750853242,
+      "grad_norm": 0.15028750896453857,
+      "learning_rate": 5.300244792574743e-06,
+      "loss": 0.3966,
+      "step": 176
+    },
+    {
+      "epoch": 0.4832764505119454,
+      "grad_norm": 0.17664162814617157,
+      "learning_rate": 5.257393773851733e-06,
+      "loss": 0.4125,
+      "step": 177
+    },
+    {
+      "epoch": 0.48600682593856653,
+      "grad_norm": 0.16111449897289276,
+      "learning_rate": 5.214523790997773e-06,
+      "loss": 0.4046,
+      "step": 178
+    },
+    {
+      "epoch": 0.4887372013651877,
+      "grad_norm": 0.17330825328826904,
+      "learning_rate": 5.171638002566218e-06,
+      "loss": 0.4054,
+      "step": 179
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.1512707620859146,
+      "learning_rate": 5.1287395682749444e-06,
+      "loss": 0.4014,
+      "step": 180
+    },
+    {
+      "epoch": 0.49419795221843005,
+      "grad_norm": 0.15316011011600494,
+      "learning_rate": 5.0858316487735385e-06,
+      "loss": 0.4013,
+      "step": 181
+    },
+    {
+      "epoch": 0.4969283276450512,
+      "grad_norm": 0.14988335967063904,
+      "learning_rate": 5.042917405410436e-06,
+      "loss": 0.3953,
+      "step": 182
+    },
+    {
+      "epoch": 0.49965870307167237,
+      "grad_norm": 0.17286710441112518,
+      "learning_rate": 5e-06,
+      "loss": 0.407,
+      "step": 183
+    },
+    {
+      "epoch": 0.5023890784982935,
+      "grad_norm": 0.16462546586990356,
+      "learning_rate": 4.957082594589566e-06,
+      "loss": 0.4017,
+      "step": 184
+    },
+    {
+      "epoch": 0.5051194539249146,
+      "grad_norm": 0.15909536182880402,
+      "learning_rate": 4.914168351226463e-06,
+      "loss": 0.3977,
+      "step": 185
+    },
+    {
+      "epoch": 0.5078498293515359,
+      "grad_norm": 0.1730009764432907,
+      "learning_rate": 4.871260431725058e-06,
+      "loss": 0.4271,
+      "step": 186
+    },
+    {
+      "epoch": 0.510580204778157,
+      "grad_norm": 0.17171163856983185,
+      "learning_rate": 4.828361997433783e-06,
+      "loss": 0.4169,
+      "step": 187
+    },
+    {
+      "epoch": 0.5133105802047782,
+      "grad_norm": 0.14412260055541992,
+      "learning_rate": 4.7854762090022274e-06,
+      "loss": 0.3782,
+      "step": 188
+    },
+    {
+      "epoch": 0.5160409556313993,
+      "grad_norm": 0.1570647805929184,
+      "learning_rate": 4.742606226148268e-06,
+      "loss": 0.4034,
+      "step": 189
+    },
+    {
+      "epoch": 0.5187713310580204,
+      "grad_norm": 0.14350539445877075,
+      "learning_rate": 4.699755207425259e-06,
+      "loss": 0.403,
+      "step": 190
+    },
+    {
+      "epoch": 0.5215017064846417,
+      "grad_norm": 0.17106682062149048,
+      "learning_rate": 4.65692630998933e-06,
+      "loss": 0.4087,
+      "step": 191
+    },
+    {
+      "epoch": 0.5242320819112628,
+      "grad_norm": 0.18561221659183502,
+      "learning_rate": 4.614122689366769e-06,
+      "loss": 0.4093,
+      "step": 192
+    },
+    {
+      "epoch": 0.5269624573378839,
+      "grad_norm": 0.15318401157855988,
+      "learning_rate": 4.571347499221528e-06,
+      "loss": 0.4,
+      "step": 193
+    },
+    {
+      "epoch": 0.5296928327645051,
+      "grad_norm": 0.150321364402771,
+      "learning_rate": 4.528603891122878e-06,
+      "loss": 0.4028,
+      "step": 194
+    },
+    {
+      "epoch": 0.5324232081911263,
+      "grad_norm": 0.15496495366096497,
+      "learning_rate": 4.485895014313198e-06,
+      "loss": 0.418,
+      "step": 195
+    },
+    {
+      "epoch": 0.5351535836177475,
+      "grad_norm": 0.1591518372297287,
+      "learning_rate": 4.443224015475956e-06,
+      "loss": 0.4122,
+      "step": 196
+    },
+    {
+      "epoch": 0.5378839590443686,
+      "grad_norm": 0.16226577758789062,
+      "learning_rate": 4.400594038503864e-06,
+      "loss": 0.4249,
+      "step": 197
+    },
+    {
+      "epoch": 0.5406143344709897,
+      "grad_norm": 0.21725980937480927,
+      "learning_rate": 4.358008224267245e-06,
+      "loss": 0.4005,
+      "step": 198
+    },
+    {
+      "epoch": 0.543344709897611,
+      "grad_norm": 0.16464541852474213,
+      "learning_rate": 4.3154697103826235e-06,
+      "loss": 0.4058,
+      "step": 199
+    },
+    {
+      "epoch": 0.5460750853242321,
+      "grad_norm": 0.15310809016227722,
+      "learning_rate": 4.272981630981551e-06,
+      "loss": 0.4049,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.3763347534905344e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2894cbb412e8163f51ee66bc37edad64bb67e6527266f7add94fd1e6f4dbcfc6
+size 6968

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models/DeepSeek-R1-Distill-Qwen-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/DeepSeek-R1-Distill-Qwen-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8080ffe6a1af1c8350d2369eee2869e363682180cd861029a525ee8157ad098b
+size 161496088

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{%- if messages|length == 1 and messages[0]['role'] == 'assistant' -%}{%- if messages[0]['content'] is not none -%}{{'<｜Assistant｜>' + messages[0]['content'] + '<｜end▁of▁sentence｜>'}}{%- endif -%}{%- else -%}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{{'<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor -%}{%- endif -%}{% if add_generation_prompt %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,2133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8191126279863481,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027303754266211604,
+      "grad_norm": 3.856764554977417,
+      "learning_rate": 9.999815806238551e-06,
+      "loss": 0.5425,
+      "step": 1
+    },
+    {
+      "epoch": 0.005460750853242321,
+      "grad_norm": 3.6394715309143066,
+      "learning_rate": 9.999263238525135e-06,
+      "loss": 0.5588,
+      "step": 2
+    },
+    {
+      "epoch": 0.008191126279863481,
+      "grad_norm": 3.228754758834839,
+      "learning_rate": 9.998342337571566e-06,
+      "loss": 0.5072,
+      "step": 3
+    },
+    {
+      "epoch": 0.010921501706484642,
+      "grad_norm": 2.7734687328338623,
+      "learning_rate": 9.997053171227527e-06,
+      "loss": 0.524,
+      "step": 4
+    },
+    {
+      "epoch": 0.013651877133105802,
+      "grad_norm": 2.6146395206451416,
+      "learning_rate": 9.995395834475578e-06,
+      "loss": 0.5013,
+      "step": 5
+    },
+    {
+      "epoch": 0.016382252559726963,
+      "grad_norm": 2.3134093284606934,
+      "learning_rate": 9.993370449424153e-06,
+      "loss": 0.5021,
+      "step": 6
+    },
+    {
+      "epoch": 0.01911262798634812,
+      "grad_norm": 2.46028995513916,
+      "learning_rate": 9.990977165298571e-06,
+      "loss": 0.5048,
+      "step": 7
+    },
+    {
+      "epoch": 0.021843003412969283,
+      "grad_norm": 2.1209499835968018,
+      "learning_rate": 9.988216158430033e-06,
+      "loss": 0.4865,
+      "step": 8
+    },
+    {
+      "epoch": 0.024573378839590442,
+      "grad_norm": 2.0378663539886475,
+      "learning_rate": 9.985087632242634e-06,
+      "loss": 0.5033,
+      "step": 9
+    },
+    {
+      "epoch": 0.027303754266211604,
+      "grad_norm": 1.8533931970596313,
+      "learning_rate": 9.981591817238379e-06,
+      "loss": 0.4731,
+      "step": 10
+    },
+    {
+      "epoch": 0.030034129692832763,
+      "grad_norm": 1.7073378562927246,
+      "learning_rate": 9.977728970980193e-06,
+      "loss": 0.4592,
+      "step": 11
+    },
+    {
+      "epoch": 0.032764505119453925,
+      "grad_norm": 1.763203501701355,
+      "learning_rate": 9.973499378072947e-06,
+      "loss": 0.4569,
+      "step": 12
+    },
+    {
+      "epoch": 0.03549488054607509,
+      "grad_norm": 1.2629003524780273,
+      "learning_rate": 9.968903350142494e-06,
+      "loss": 0.4364,
+      "step": 13
+    },
+    {
+      "epoch": 0.03822525597269624,
+      "grad_norm": 1.345859408378601,
+      "learning_rate": 9.9639412258127e-06,
+      "loss": 0.4737,
+      "step": 14
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 1.291548490524292,
+      "learning_rate": 9.958613370680507e-06,
+      "loss": 0.4504,
+      "step": 15
+    },
+    {
+      "epoch": 0.04368600682593857,
+      "grad_norm": 1.3444461822509766,
+      "learning_rate": 9.952920177288985e-06,
+      "loss": 0.457,
+      "step": 16
+    },
+    {
+      "epoch": 0.04641638225255973,
+      "grad_norm": 1.5857586860656738,
+      "learning_rate": 9.946862065098415e-06,
+      "loss": 0.4696,
+      "step": 17
+    },
+    {
+      "epoch": 0.049146757679180884,
+      "grad_norm": 1.1109745502471924,
+      "learning_rate": 9.940439480455386e-06,
+      "loss": 0.4417,
+      "step": 18
+    },
+    {
+      "epoch": 0.05187713310580205,
+      "grad_norm": 1.1297810077667236,
+      "learning_rate": 9.933652896559907e-06,
+      "loss": 0.4463,
+      "step": 19
+    },
+    {
+      "epoch": 0.05460750853242321,
+      "grad_norm": 1.0981742143630981,
+      "learning_rate": 9.926502813430545e-06,
+      "loss": 0.4499,
+      "step": 20
+    },
+    {
+      "epoch": 0.05733788395904437,
+      "grad_norm": 1.1592185497283936,
+      "learning_rate": 9.918989757867584e-06,
+      "loss": 0.447,
+      "step": 21
+    },
+    {
+      "epoch": 0.060068259385665526,
+      "grad_norm": 1.0812605619430542,
+      "learning_rate": 9.911114283414204e-06,
+      "loss": 0.4638,
+      "step": 22
+    },
+    {
+      "epoch": 0.06279863481228669,
+      "grad_norm": 0.774226188659668,
+      "learning_rate": 9.902876970315715e-06,
+      "loss": 0.4439,
+      "step": 23
+    },
+    {
+      "epoch": 0.06552901023890785,
+      "grad_norm": 0.7117806673049927,
+      "learning_rate": 9.89427842547679e-06,
+      "loss": 0.4424,
+      "step": 24
+    },
+    {
+      "epoch": 0.06825938566552901,
+      "grad_norm": 0.7732372283935547,
+      "learning_rate": 9.885319282416755e-06,
+      "loss": 0.4494,
+      "step": 25
+    },
+    {
+      "epoch": 0.07098976109215017,
+      "grad_norm": 0.7167857885360718,
+      "learning_rate": 9.876000201222912e-06,
+      "loss": 0.4514,
+      "step": 26
+    },
+    {
+      "epoch": 0.07372013651877134,
+      "grad_norm": 0.7761046290397644,
+      "learning_rate": 9.866321868501914e-06,
+      "loss": 0.462,
+      "step": 27
+    },
+    {
+      "epoch": 0.07645051194539249,
+      "grad_norm": 0.5660157203674316,
+      "learning_rate": 9.856284997329158e-06,
+      "loss": 0.4455,
+      "step": 28
+    },
+    {
+      "epoch": 0.07918088737201365,
+      "grad_norm": 0.5861382484436035,
+      "learning_rate": 9.845890327196269e-06,
+      "loss": 0.4416,
+      "step": 29
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 0.7201432585716248,
+      "learning_rate": 9.835138623956603e-06,
+      "loss": 0.4209,
+      "step": 30
+    },
+    {
+      "epoch": 0.08464163822525597,
+      "grad_norm": 0.8803044557571411,
+      "learning_rate": 9.824030679768824e-06,
+      "loss": 0.4276,
+      "step": 31
+    },
+    {
+      "epoch": 0.08737201365187713,
+      "grad_norm": 0.7925510406494141,
+      "learning_rate": 9.812567313038542e-06,
+      "loss": 0.4473,
+      "step": 32
+    },
+    {
+      "epoch": 0.0901023890784983,
+      "grad_norm": 0.9926882982254028,
+      "learning_rate": 9.80074936835801e-06,
+      "loss": 0.4398,
+      "step": 33
+    },
+    {
+      "epoch": 0.09283276450511946,
+      "grad_norm": 0.8362368941307068,
+      "learning_rate": 9.788577716443903e-06,
+      "loss": 0.4347,
+      "step": 34
+    },
+    {
+      "epoch": 0.09556313993174062,
+      "grad_norm": 0.8301376104354858,
+      "learning_rate": 9.77605325407316e-06,
+      "loss": 0.4684,
+      "step": 35
+    },
+    {
+      "epoch": 0.09829351535836177,
+      "grad_norm": 0.7239497900009155,
+      "learning_rate": 9.763176904016914e-06,
+      "loss": 0.4686,
+      "step": 36
+    },
+    {
+      "epoch": 0.10102389078498293,
+      "grad_norm": 0.6108490824699402,
+      "learning_rate": 9.749949614972507e-06,
+      "loss": 0.431,
+      "step": 37
+    },
+    {
+      "epoch": 0.1037542662116041,
+      "grad_norm": 0.5505651235580444,
+      "learning_rate": 9.736372361493584e-06,
+      "loss": 0.4383,
+      "step": 38
+    },
+    {
+      "epoch": 0.10648464163822526,
+      "grad_norm": 0.5642620325088501,
+      "learning_rate": 9.722446143918307e-06,
+      "loss": 0.4249,
+      "step": 39
+    },
+    {
+      "epoch": 0.10921501706484642,
+      "grad_norm": 0.4733835458755493,
+      "learning_rate": 9.70817198829563e-06,
+      "loss": 0.4404,
+      "step": 40
+    },
+    {
+      "epoch": 0.11194539249146758,
+      "grad_norm": 0.43274644017219543,
+      "learning_rate": 9.693550946309721e-06,
+      "loss": 0.428,
+      "step": 41
+    },
+    {
+      "epoch": 0.11467576791808874,
+      "grad_norm": 0.45345625281333923,
+      "learning_rate": 9.678584095202468e-06,
+      "loss": 0.4559,
+      "step": 42
+    },
+    {
+      "epoch": 0.1174061433447099,
+      "grad_norm": 0.3903965353965759,
+      "learning_rate": 9.663272537694112e-06,
+      "loss": 0.4419,
+      "step": 43
+    },
+    {
+      "epoch": 0.12013651877133105,
+      "grad_norm": 0.5206829905509949,
+      "learning_rate": 9.647617401902003e-06,
+      "loss": 0.4366,
+      "step": 44
+    },
+    {
+      "epoch": 0.12286689419795221,
+      "grad_norm": 0.38311880826950073,
+      "learning_rate": 9.631619841257477e-06,
+      "loss": 0.4289,
+      "step": 45
+    },
+    {
+      "epoch": 0.12559726962457338,
+      "grad_norm": 0.4225156903266907,
+      "learning_rate": 9.615281034420882e-06,
+      "loss": 0.4215,
+      "step": 46
+    },
+    {
+      "epoch": 0.12832764505119454,
+      "grad_norm": 0.4255654513835907,
+      "learning_rate": 9.598602185194733e-06,
+      "loss": 0.4247,
+      "step": 47
+    },
+    {
+      "epoch": 0.1310580204778157,
+      "grad_norm": 0.4347112774848938,
+      "learning_rate": 9.581584522435025e-06,
+      "loss": 0.427,
+      "step": 48
+    },
+    {
+      "epoch": 0.13378839590443686,
+      "grad_norm": 0.34471118450164795,
+      "learning_rate": 9.564229299960679e-06,
+      "loss": 0.421,
+      "step": 49
+    },
+    {
+      "epoch": 0.13651877133105803,
+      "grad_norm": 0.43423381447792053,
+      "learning_rate": 9.54653779646118e-06,
+      "loss": 0.4322,
+      "step": 50
+    },
+    {
+      "epoch": 0.1392491467576792,
+      "grad_norm": 0.4541296064853668,
+      "learning_rate": 9.528511315402358e-06,
+      "loss": 0.4212,
+      "step": 51
+    },
+    {
+      "epoch": 0.14197952218430035,
+      "grad_norm": 0.29571640491485596,
+      "learning_rate": 9.510151184930354e-06,
+      "loss": 0.4312,
+      "step": 52
+    },
+    {
+      "epoch": 0.1447098976109215,
+      "grad_norm": 0.30192604660987854,
+      "learning_rate": 9.491458757773766e-06,
+      "loss": 0.4328,
+      "step": 53
+    },
+    {
+      "epoch": 0.14744027303754267,
+      "grad_norm": 0.24025903642177582,
+      "learning_rate": 9.472435411143979e-06,
+      "loss": 0.4214,
+      "step": 54
+    },
+    {
+      "epoch": 0.15017064846416384,
+      "grad_norm": 0.3551096022129059,
+      "learning_rate": 9.453082546633704e-06,
+      "loss": 0.4232,
+      "step": 55
+    },
+    {
+      "epoch": 0.15290102389078497,
+      "grad_norm": 0.2226678431034088,
+      "learning_rate": 9.433401590113702e-06,
+      "loss": 0.4332,
+      "step": 56
+    },
+    {
+      "epoch": 0.15563139931740613,
+      "grad_norm": 0.21858179569244385,
+      "learning_rate": 9.413393991627737e-06,
+      "loss": 0.418,
+      "step": 57
+    },
+    {
+      "epoch": 0.1583617747440273,
+      "grad_norm": 0.22533869743347168,
+      "learning_rate": 9.393061225285743e-06,
+      "loss": 0.4361,
+      "step": 58
+    },
+    {
+      "epoch": 0.16109215017064846,
+      "grad_norm": 0.21001799404621124,
+      "learning_rate": 9.372404789155199e-06,
+      "loss": 0.4187,
+      "step": 59
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.20293086767196655,
+      "learning_rate": 9.351426205150778e-06,
+      "loss": 0.4252,
+      "step": 60
+    },
+    {
+      "epoch": 0.16655290102389078,
+      "grad_norm": 0.22262097895145416,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.4442,
+      "step": 61
+    },
+    {
+      "epoch": 0.16928327645051194,
+      "grad_norm": 0.21581031382083893,
+      "learning_rate": 9.30850879974034e-06,
+      "loss": 0.4233,
+      "step": 62
+    },
+    {
+      "epoch": 0.1720136518771331,
+      "grad_norm": 0.2510773837566376,
+      "learning_rate": 9.286573140381663e-06,
+      "loss": 0.4126,
+      "step": 63
+    },
+    {
+      "epoch": 0.17474402730375427,
+      "grad_norm": 0.22764866054058075,
+      "learning_rate": 9.2643216570108e-06,
+      "loss": 0.4435,
+      "step": 64
+    },
+    {
+      "epoch": 0.17747440273037543,
+      "grad_norm": 0.2921380400657654,
+      "learning_rate": 9.24175598906152e-06,
+      "loss": 0.4006,
+      "step": 65
+    },
+    {
+      "epoch": 0.1802047781569966,
+      "grad_norm": 0.2642498314380646,
+      "learning_rate": 9.218877799115929e-06,
+      "loss": 0.4224,
+      "step": 66
+    },
+    {
+      "epoch": 0.18293515358361775,
+      "grad_norm": 0.2313549965620041,
+      "learning_rate": 9.19568877278197e-06,
+      "loss": 0.413,
+      "step": 67
+    },
+    {
+      "epoch": 0.18566552901023892,
+      "grad_norm": 0.2201680839061737,
+      "learning_rate": 9.172190618569236e-06,
+      "loss": 0.4278,
+      "step": 68
+    },
+    {
+      "epoch": 0.18839590443686008,
+      "grad_norm": 0.2556556463241577,
+      "learning_rate": 9.148385067763094e-06,
+      "loss": 0.4216,
+      "step": 69
+    },
+    {
+      "epoch": 0.19112627986348124,
+      "grad_norm": 0.238591730594635,
+      "learning_rate": 9.124273874297123e-06,
+      "loss": 0.4217,
+      "step": 70
+    },
+    {
+      "epoch": 0.19385665529010238,
+      "grad_norm": 0.2658149302005768,
+      "learning_rate": 9.099858814623887e-06,
+      "loss": 0.4159,
+      "step": 71
+    },
+    {
+      "epoch": 0.19658703071672354,
+      "grad_norm": 0.26856058835983276,
+      "learning_rate": 9.075141687584056e-06,
+      "loss": 0.4285,
+      "step": 72
+    },
+    {
+      "epoch": 0.1993174061433447,
+      "grad_norm": 0.1793709248304367,
+      "learning_rate": 9.050124314273876e-06,
+      "loss": 0.4255,
+      "step": 73
+    },
+    {
+      "epoch": 0.20204778156996586,
+      "grad_norm": 0.1868457794189453,
+      "learning_rate": 9.024808537910981e-06,
+      "loss": 0.417,
+      "step": 74
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.19721131026744843,
+      "learning_rate": 8.999196223698599e-06,
+      "loss": 0.4234,
+      "step": 75
+    },
+    {
+      "epoch": 0.2075085324232082,
+      "grad_norm": 0.1849862039089203,
+      "learning_rate": 8.973289258688125e-06,
+      "loss": 0.3868,
+      "step": 76
+    },
+    {
+      "epoch": 0.21023890784982935,
+      "grad_norm": 0.18427810072898865,
+      "learning_rate": 8.9470895516401e-06,
+      "loss": 0.4205,
+      "step": 77
+    },
+    {
+      "epoch": 0.2129692832764505,
+      "grad_norm": 0.22481605410575867,
+      "learning_rate": 8.920599032883553e-06,
+      "loss": 0.4271,
+      "step": 78
+    },
+    {
+      "epoch": 0.21569965870307167,
+      "grad_norm": 0.18275555968284607,
+      "learning_rate": 8.893819654173804e-06,
+      "loss": 0.4276,
+      "step": 79
+    },
+    {
+      "epoch": 0.21843003412969283,
+      "grad_norm": 0.17510327696800232,
+      "learning_rate": 8.86675338854865e-06,
+      "loss": 0.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.221160409556314,
+      "grad_norm": 0.18124502897262573,
+      "learning_rate": 8.839402230183e-06,
+      "loss": 0.4181,
+      "step": 81
+    },
+    {
+      "epoch": 0.22389078498293516,
+      "grad_norm": 0.1930208057165146,
+      "learning_rate": 8.811768194241951e-06,
+      "loss": 0.4326,
+      "step": 82
+    },
+    {
+      "epoch": 0.22662116040955632,
+      "grad_norm": 0.17881739139556885,
+      "learning_rate": 8.783853316732313e-06,
+      "loss": 0.4227,
+      "step": 83
+    },
+    {
+      "epoch": 0.22935153583617748,
+      "grad_norm": 0.18276868760585785,
+      "learning_rate": 8.755659654352599e-06,
+      "loss": 0.4109,
+      "step": 84
+    },
+    {
+      "epoch": 0.23208191126279865,
+      "grad_norm": 0.1769554764032364,
+      "learning_rate": 8.727189284341501e-06,
+      "loss": 0.4267,
+      "step": 85
+    },
+    {
+      "epoch": 0.2348122866894198,
+      "grad_norm": 0.22149443626403809,
+      "learning_rate": 8.698444304324837e-06,
+      "loss": 0.4236,
+      "step": 86
+    },
+    {
+      "epoch": 0.23754266211604094,
+      "grad_norm": 0.1817912608385086,
+      "learning_rate": 8.669426832160997e-06,
+      "loss": 0.4235,
+      "step": 87
+    },
+    {
+      "epoch": 0.2402730375426621,
+      "grad_norm": 0.23118089139461517,
+      "learning_rate": 8.640139005784924e-06,
+      "loss": 0.4338,
+      "step": 88
+    },
+    {
+      "epoch": 0.24300341296928327,
+      "grad_norm": 0.23663879930973053,
+      "learning_rate": 8.610582983050581e-06,
+      "loss": 0.4239,
+      "step": 89
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.16908958554267883,
+      "learning_rate": 8.580760941571968e-06,
+      "loss": 0.4148,
+      "step": 90
+    },
+    {
+      "epoch": 0.2484641638225256,
+      "grad_norm": 0.23422765731811523,
+      "learning_rate": 8.55067507856268e-06,
+      "loss": 0.4183,
+      "step": 91
+    },
+    {
+      "epoch": 0.25119453924914675,
+      "grad_norm": 0.24864593148231506,
+      "learning_rate": 8.520327610674029e-06,
+      "loss": 0.41,
+      "step": 92
+    },
+    {
+      "epoch": 0.25392491467576794,
+      "grad_norm": 0.20847055315971375,
+      "learning_rate": 8.489720773831717e-06,
+      "loss": 0.4221,
+      "step": 93
+    },
+    {
+      "epoch": 0.2566552901023891,
+      "grad_norm": 0.19055533409118652,
+      "learning_rate": 8.458856823071111e-06,
+      "loss": 0.4191,
+      "step": 94
+    },
+    {
+      "epoch": 0.2593856655290102,
+      "grad_norm": 0.24293097853660583,
+      "learning_rate": 8.427738032371078e-06,
+      "loss": 0.3906,
+      "step": 95
+    },
+    {
+      "epoch": 0.2621160409556314,
+      "grad_norm": 0.23974299430847168,
+      "learning_rate": 8.396366694486466e-06,
+      "loss": 0.4157,
+      "step": 96
+    },
+    {
+      "epoch": 0.26484641638225254,
+      "grad_norm": 0.1998283416032791,
+      "learning_rate": 8.364745120779166e-06,
+      "loss": 0.4054,
+      "step": 97
+    },
+    {
+      "epoch": 0.2675767918088737,
+      "grad_norm": 0.21701572835445404,
+      "learning_rate": 8.332875641047817e-06,
+      "loss": 0.3984,
+      "step": 98
+    },
+    {
+      "epoch": 0.27030716723549486,
+      "grad_norm": 0.18561778962612152,
+      "learning_rate": 8.30076060335616e-06,
+      "loss": 0.4164,
+      "step": 99
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 0.1797938048839569,
+      "learning_rate": 8.26840237386003e-06,
+      "loss": 0.4339,
+      "step": 100
+    },
+    {
+      "epoch": 0.2757679180887372,
+      "grad_norm": 0.1605861335992813,
+      "learning_rate": 8.235803336633033e-06,
+      "loss": 0.4053,
+      "step": 101
+    },
+    {
+      "epoch": 0.2784982935153584,
+      "grad_norm": 0.1774858683347702,
+      "learning_rate": 8.202965893490877e-06,
+      "loss": 0.4232,
+      "step": 102
+    },
+    {
+      "epoch": 0.2812286689419795,
+      "grad_norm": 0.15541759133338928,
+      "learning_rate": 8.169892463814435e-06,
+      "loss": 0.4208,
+      "step": 103
+    },
+    {
+      "epoch": 0.2839590443686007,
+      "grad_norm": 0.16066958010196686,
+      "learning_rate": 8.136585484371471e-06,
+      "loss": 0.4074,
+      "step": 104
+    },
+    {
+      "epoch": 0.28668941979522183,
+      "grad_norm": 0.1789342761039734,
+      "learning_rate": 8.103047409137114e-06,
+      "loss": 0.4104,
+      "step": 105
+    },
+    {
+      "epoch": 0.289419795221843,
+      "grad_norm": 0.16283057630062103,
+      "learning_rate": 8.06928070911306e-06,
+      "loss": 0.4073,
+      "step": 106
+    },
+    {
+      "epoch": 0.29215017064846416,
+      "grad_norm": 0.17041556537151337,
+      "learning_rate": 8.035287872145502e-06,
+      "loss": 0.4396,
+      "step": 107
+    },
+    {
+      "epoch": 0.29488054607508535,
+      "grad_norm": 0.17072531580924988,
+      "learning_rate": 8.001071402741843e-06,
+      "loss": 0.4297,
+      "step": 108
+    },
+    {
+      "epoch": 0.2976109215017065,
+      "grad_norm": 0.16717186570167542,
+      "learning_rate": 7.96663382188616e-06,
+      "loss": 0.408,
+      "step": 109
+    },
+    {
+      "epoch": 0.3003412969283277,
+      "grad_norm": 0.16995355486869812,
+      "learning_rate": 7.93197766685348e-06,
+      "loss": 0.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.3030716723549488,
+      "grad_norm": 0.1682933270931244,
+      "learning_rate": 7.897105491022819e-06,
+      "loss": 0.4179,
+      "step": 111
+    },
+    {
+      "epoch": 0.30580204778156994,
+      "grad_norm": 0.15432436764240265,
+      "learning_rate": 7.862019863689075e-06,
+      "loss": 0.4037,
+      "step": 112
+    },
+    {
+      "epoch": 0.30853242320819113,
+      "grad_norm": 0.16314339637756348,
+      "learning_rate": 7.826723369873715e-06,
+      "loss": 0.4066,
+      "step": 113
+    },
+    {
+      "epoch": 0.31126279863481227,
+      "grad_norm": 0.17164085805416107,
+      "learning_rate": 7.791218610134324e-06,
+      "loss": 0.4328,
+      "step": 114
+    },
+    {
+      "epoch": 0.31399317406143346,
+      "grad_norm": 0.16329169273376465,
+      "learning_rate": 7.755508200373e-06,
+      "loss": 0.41,
+      "step": 115
+    },
+    {
+      "epoch": 0.3167235494880546,
+      "grad_norm": 0.15500546991825104,
+      "learning_rate": 7.719594771643623e-06,
+      "loss": 0.4023,
+      "step": 116
+    },
+    {
+      "epoch": 0.3194539249146758,
+      "grad_norm": 0.16174261271953583,
+      "learning_rate": 7.683480969958005e-06,
+      "loss": 0.4147,
+      "step": 117
+    },
+    {
+      "epoch": 0.3221843003412969,
+      "grad_norm": 0.16179116070270538,
+      "learning_rate": 7.647169456090925e-06,
+      "loss": 0.4198,
+      "step": 118
+    },
+    {
+      "epoch": 0.3249146757679181,
+      "grad_norm": 0.1634499430656433,
+      "learning_rate": 7.6106629053841255e-06,
+      "loss": 0.4162,
+      "step": 119
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.17482595145702362,
+      "learning_rate": 7.5739640075491546e-06,
+      "loss": 0.4304,
+      "step": 120
+    },
+    {
+      "epoch": 0.33037542662116043,
+      "grad_norm": 0.16381986439228058,
+      "learning_rate": 7.537075466469228e-06,
+      "loss": 0.4076,
+      "step": 121
+    },
+    {
+      "epoch": 0.33310580204778156,
+      "grad_norm": 0.15148329734802246,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3943,
+      "step": 122
+    },
+    {
+      "epoch": 0.33583617747440275,
+      "grad_norm": 0.17150920629501343,
+      "learning_rate": 7.462740339769323e-06,
+      "loss": 0.4221,
+      "step": 123
+    },
+    {
+      "epoch": 0.3385665529010239,
+      "grad_norm": 0.16451485455036163,
+      "learning_rate": 7.425299230975982e-06,
+      "loss": 0.3909,
+      "step": 124
+    },
+    {
+      "epoch": 0.3412969283276451,
+      "grad_norm": 0.1635640561580658,
+      "learning_rate": 7.387679432187442e-06,
+      "loss": 0.412,
+      "step": 125
+    },
+    {
+      "epoch": 0.3440273037542662,
+      "grad_norm": 0.15344786643981934,
+      "learning_rate": 7.349883715136601e-06,
+      "loss": 0.3957,
+      "step": 126
+    },
+    {
+      "epoch": 0.34675767918088735,
+      "grad_norm": 0.20929256081581116,
+      "learning_rate": 7.311914864517575e-06,
+      "loss": 0.4172,
+      "step": 127
+    },
+    {
+      "epoch": 0.34948805460750854,
+      "grad_norm": 0.15553469955921173,
+      "learning_rate": 7.27377567778053e-06,
+      "loss": 0.4255,
+      "step": 128
+    },
+    {
+      "epoch": 0.35221843003412967,
+      "grad_norm": 0.16687364876270294,
+      "learning_rate": 7.235468964925571e-06,
+      "loss": 0.4032,
+      "step": 129
+    },
+    {
+      "epoch": 0.35494880546075086,
+      "grad_norm": 0.15902447700500488,
+      "learning_rate": 7.1969975482957075e-06,
+      "loss": 0.4264,
+      "step": 130
+    },
+    {
+      "epoch": 0.357679180887372,
+      "grad_norm": 0.16279031336307526,
+      "learning_rate": 7.158364262368919e-06,
+      "loss": 0.4081,
+      "step": 131
+    },
+    {
+      "epoch": 0.3604095563139932,
+      "grad_norm": 0.1744302660226822,
+      "learning_rate": 7.119571953549305e-06,
+      "loss": 0.4439,
+      "step": 132
+    },
+    {
+      "epoch": 0.3631399317406143,
+      "grad_norm": 0.16045725345611572,
+      "learning_rate": 7.080623479957372e-06,
+      "loss": 0.3996,
+      "step": 133
+    },
+    {
+      "epoch": 0.3658703071672355,
+      "grad_norm": 0.16313788294792175,
+      "learning_rate": 7.041521711219468e-06,
+      "loss": 0.4055,
+      "step": 134
+    },
+    {
+      "epoch": 0.36860068259385664,
+      "grad_norm": 0.15558135509490967,
+      "learning_rate": 7.002269528256334e-06,
+      "loss": 0.4074,
+      "step": 135
+    },
+    {
+      "epoch": 0.37133105802047783,
+      "grad_norm": 0.16284853219985962,
+      "learning_rate": 6.9628698230708604e-06,
+      "loss": 0.3937,
+      "step": 136
+    },
+    {
+      "epoch": 0.37406143344709897,
+      "grad_norm": 0.1701689511537552,
+      "learning_rate": 6.9233254985350066e-06,
+      "loss": 0.4014,
+      "step": 137
+    },
+    {
+      "epoch": 0.37679180887372016,
+      "grad_norm": 0.16153037548065186,
+      "learning_rate": 6.883639468175926e-06,
+      "loss": 0.4345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3795221843003413,
+      "grad_norm": 0.15898269414901733,
+      "learning_rate": 6.843814655961302e-06,
+      "loss": 0.4117,
+      "step": 139
+    },
+    {
+      "epoch": 0.3822525597269625,
+      "grad_norm": 0.15082918107509613,
+      "learning_rate": 6.803853996083918e-06,
+      "loss": 0.4041,
+      "step": 140
+    },
+    {
+      "epoch": 0.3849829351535836,
+      "grad_norm": 0.15225613117218018,
+      "learning_rate": 6.763760432745475e-06,
+      "loss": 0.4203,
+      "step": 141
+    },
+    {
+      "epoch": 0.38771331058020475,
+      "grad_norm": 0.15860538184642792,
+      "learning_rate": 6.723536919939669e-06,
+      "loss": 0.409,
+      "step": 142
+    },
+    {
+      "epoch": 0.39044368600682594,
+      "grad_norm": 0.15701624751091003,
+      "learning_rate": 6.683186421234552e-06,
+      "loss": 0.411,
+      "step": 143
+    },
+    {
+      "epoch": 0.3931740614334471,
+      "grad_norm": 0.1592189222574234,
+      "learning_rate": 6.6427119095541745e-06,
+      "loss": 0.4034,
+      "step": 144
+    },
+    {
+      "epoch": 0.39590443686006827,
+      "grad_norm": 0.16646814346313477,
+      "learning_rate": 6.602116366959556e-06,
+      "loss": 0.411,
+      "step": 145
+    },
+    {
+      "epoch": 0.3986348122866894,
+      "grad_norm": 0.16729459166526794,
+      "learning_rate": 6.561402784428974e-06,
+      "loss": 0.4032,
+      "step": 146
+    },
+    {
+      "epoch": 0.4013651877133106,
+      "grad_norm": 0.16820791363716125,
+      "learning_rate": 6.520574161637591e-06,
+      "loss": 0.4087,
+      "step": 147
+    },
+    {
+      "epoch": 0.4040955631399317,
+      "grad_norm": 0.17279136180877686,
+      "learning_rate": 6.479633506736447e-06,
+      "loss": 0.3949,
+      "step": 148
+    },
+    {
+      "epoch": 0.4068259385665529,
+      "grad_norm": 0.15827003121376038,
+      "learning_rate": 6.438583836130835e-06,
+      "loss": 0.4134,
+      "step": 149
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.3199061155319214,
+      "learning_rate": 6.397428174258048e-06,
+      "loss": 0.3956,
+      "step": 150
+    },
+    {
+      "epoch": 0.41228668941979524,
+      "grad_norm": 0.15721672773361206,
+      "learning_rate": 6.3561695533645505e-06,
+      "loss": 0.408,
+      "step": 151
+    },
+    {
+      "epoch": 0.4150170648464164,
+      "grad_norm": 0.16460402309894562,
+      "learning_rate": 6.314811013282574e-06,
+      "loss": 0.4083,
+      "step": 152
+    },
+    {
+      "epoch": 0.41774744027303756,
+      "grad_norm": 0.156940758228302,
+      "learning_rate": 6.273355601206143e-06,
+      "loss": 0.4062,
+      "step": 153
+    },
+    {
+      "epoch": 0.4204778156996587,
+      "grad_norm": 0.15688540041446686,
+      "learning_rate": 6.231806371466574e-06,
+      "loss": 0.4051,
+      "step": 154
+    },
+    {
+      "epoch": 0.4232081911262799,
+      "grad_norm": 0.14866897463798523,
+      "learning_rate": 6.190166385307428e-06,
+      "loss": 0.4047,
+      "step": 155
+    },
+    {
+      "epoch": 0.425938566552901,
+      "grad_norm": 0.15852367877960205,
+      "learning_rate": 6.148438710658979e-06,
+      "loss": 0.4043,
+      "step": 156
+    },
+    {
+      "epoch": 0.4286689419795222,
+      "grad_norm": 0.1479935199022293,
+      "learning_rate": 6.106626421912163e-06,
+      "loss": 0.4073,
+      "step": 157
+    },
+    {
+      "epoch": 0.43139931740614335,
+      "grad_norm": 0.1690177172422409,
+      "learning_rate": 6.064732599692079e-06,
+      "loss": 0.4148,
+      "step": 158
+    },
+    {
+      "epoch": 0.4341296928327645,
+      "grad_norm": 0.1765451729297638,
+      "learning_rate": 6.022760330631006e-06,
+      "loss": 0.4105,
+      "step": 159
+    },
+    {
+      "epoch": 0.43686006825938567,
+      "grad_norm": 0.16014869511127472,
+      "learning_rate": 5.980712707140985e-06,
+      "loss": 0.4138,
+      "step": 160
+    },
+    {
+      "epoch": 0.4395904436860068,
+      "grad_norm": 0.1788393259048462,
+      "learning_rate": 5.938592827185994e-06,
+      "loss": 0.4224,
+      "step": 161
+    },
+    {
+      "epoch": 0.442320819112628,
+      "grad_norm": 0.1551506668329239,
+      "learning_rate": 5.896403794053679e-06,
+      "loss": 0.4058,
+      "step": 162
+    },
+    {
+      "epoch": 0.44505119453924913,
+      "grad_norm": 0.1573813110589981,
+      "learning_rate": 5.854148716126722e-06,
+      "loss": 0.4147,
+      "step": 163
+    },
+    {
+      "epoch": 0.4477815699658703,
+      "grad_norm": 0.16244283318519592,
+      "learning_rate": 5.811830706653819e-06,
+      "loss": 0.4152,
+      "step": 164
+    },
+    {
+      "epoch": 0.45051194539249145,
+      "grad_norm": 0.17180225253105164,
+      "learning_rate": 5.76945288352031e-06,
+      "loss": 0.3972,
+      "step": 165
+    },
+    {
+      "epoch": 0.45324232081911264,
+      "grad_norm": 0.16414454579353333,
+      "learning_rate": 5.72701836901845e-06,
+      "loss": 0.403,
+      "step": 166
+    },
+    {
+      "epoch": 0.4559726962457338,
+      "grad_norm": 0.3096899092197418,
+      "learning_rate": 5.684530289617377e-06,
+      "loss": 0.4195,
+      "step": 167
+    },
+    {
+      "epoch": 0.45870307167235497,
+      "grad_norm": 0.16957193613052368,
+      "learning_rate": 5.641991775732756e-06,
+      "loss": 0.405,
+      "step": 168
+    },
+    {
+      "epoch": 0.4614334470989761,
+      "grad_norm": 0.16117002069950104,
+      "learning_rate": 5.599405961496137e-06,
+      "loss": 0.398,
+      "step": 169
+    },
+    {
+      "epoch": 0.4641638225255973,
+      "grad_norm": 0.17450742423534393,
+      "learning_rate": 5.556775984524044e-06,
+      "loss": 0.4009,
+      "step": 170
+    },
+    {
+      "epoch": 0.4668941979522184,
+      "grad_norm": 0.15785841643810272,
+      "learning_rate": 5.514104985686802e-06,
+      "loss": 0.3838,
+      "step": 171
+    },
+    {
+      "epoch": 0.4696245733788396,
+      "grad_norm": 0.22598251700401306,
+      "learning_rate": 5.471396108877123e-06,
+      "loss": 0.4176,
+      "step": 172
+    },
+    {
+      "epoch": 0.47235494880546075,
+      "grad_norm": 0.17126567661762238,
+      "learning_rate": 5.428652500778472e-06,
+      "loss": 0.4135,
+      "step": 173
+    },
+    {
+      "epoch": 0.4750853242320819,
+      "grad_norm": 0.1700679510831833,
+      "learning_rate": 5.385877310633233e-06,
+      "loss": 0.4259,
+      "step": 174
+    },
+    {
+      "epoch": 0.4778156996587031,
+      "grad_norm": 0.1624089628458023,
+      "learning_rate": 5.3430736900106715e-06,
+      "loss": 0.4425,
+      "step": 175
+    },
+    {
+      "epoch": 0.4805460750853242,
+      "grad_norm": 0.15028750896453857,
+      "learning_rate": 5.300244792574743e-06,
+      "loss": 0.3966,
+      "step": 176
+    },
+    {
+      "epoch": 0.4832764505119454,
+      "grad_norm": 0.17664162814617157,
+      "learning_rate": 5.257393773851733e-06,
+      "loss": 0.4125,
+      "step": 177
+    },
+    {
+      "epoch": 0.48600682593856653,
+      "grad_norm": 0.16111449897289276,
+      "learning_rate": 5.214523790997773e-06,
+      "loss": 0.4046,
+      "step": 178
+    },
+    {
+      "epoch": 0.4887372013651877,
+      "grad_norm": 0.17330825328826904,
+      "learning_rate": 5.171638002566218e-06,
+      "loss": 0.4054,
+      "step": 179
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.1512707620859146,
+      "learning_rate": 5.1287395682749444e-06,
+      "loss": 0.4014,
+      "step": 180
+    },
+    {
+      "epoch": 0.49419795221843005,
+      "grad_norm": 0.15316011011600494,
+      "learning_rate": 5.0858316487735385e-06,
+      "loss": 0.4013,
+      "step": 181
+    },
+    {
+      "epoch": 0.4969283276450512,
+      "grad_norm": 0.14988335967063904,
+      "learning_rate": 5.042917405410436e-06,
+      "loss": 0.3953,
+      "step": 182
+    },
+    {
+      "epoch": 0.49965870307167237,
+      "grad_norm": 0.17286710441112518,
+      "learning_rate": 5e-06,
+      "loss": 0.407,
+      "step": 183
+    },
+    {
+      "epoch": 0.5023890784982935,
+      "grad_norm": 0.16462546586990356,
+      "learning_rate": 4.957082594589566e-06,
+      "loss": 0.4017,
+      "step": 184
+    },
+    {
+      "epoch": 0.5051194539249146,
+      "grad_norm": 0.15909536182880402,
+      "learning_rate": 4.914168351226463e-06,
+      "loss": 0.3977,
+      "step": 185
+    },
+    {
+      "epoch": 0.5078498293515359,
+      "grad_norm": 0.1730009764432907,
+      "learning_rate": 4.871260431725058e-06,
+      "loss": 0.4271,
+      "step": 186
+    },
+    {
+      "epoch": 0.510580204778157,
+      "grad_norm": 0.17171163856983185,
+      "learning_rate": 4.828361997433783e-06,
+      "loss": 0.4169,
+      "step": 187
+    },
+    {
+      "epoch": 0.5133105802047782,
+      "grad_norm": 0.14412260055541992,
+      "learning_rate": 4.7854762090022274e-06,
+      "loss": 0.3782,
+      "step": 188
+    },
+    {
+      "epoch": 0.5160409556313993,
+      "grad_norm": 0.1570647805929184,
+      "learning_rate": 4.742606226148268e-06,
+      "loss": 0.4034,
+      "step": 189
+    },
+    {
+      "epoch": 0.5187713310580204,
+      "grad_norm": 0.14350539445877075,
+      "learning_rate": 4.699755207425259e-06,
+      "loss": 0.403,
+      "step": 190
+    },
+    {
+      "epoch": 0.5215017064846417,
+      "grad_norm": 0.17106682062149048,
+      "learning_rate": 4.65692630998933e-06,
+      "loss": 0.4087,
+      "step": 191
+    },
+    {
+      "epoch": 0.5242320819112628,
+      "grad_norm": 0.18561221659183502,
+      "learning_rate": 4.614122689366769e-06,
+      "loss": 0.4093,
+      "step": 192
+    },
+    {
+      "epoch": 0.5269624573378839,
+      "grad_norm": 0.15318401157855988,
+      "learning_rate": 4.571347499221528e-06,
+      "loss": 0.4,
+      "step": 193
+    },
+    {
+      "epoch": 0.5296928327645051,
+      "grad_norm": 0.150321364402771,
+      "learning_rate": 4.528603891122878e-06,
+      "loss": 0.4028,
+      "step": 194
+    },
+    {
+      "epoch": 0.5324232081911263,
+      "grad_norm": 0.15496495366096497,
+      "learning_rate": 4.485895014313198e-06,
+      "loss": 0.418,
+      "step": 195
+    },
+    {
+      "epoch": 0.5351535836177475,
+      "grad_norm": 0.1591518372297287,
+      "learning_rate": 4.443224015475956e-06,
+      "loss": 0.4122,
+      "step": 196
+    },
+    {
+      "epoch": 0.5378839590443686,
+      "grad_norm": 0.16226577758789062,
+      "learning_rate": 4.400594038503864e-06,
+      "loss": 0.4249,
+      "step": 197
+    },
+    {
+      "epoch": 0.5406143344709897,
+      "grad_norm": 0.21725980937480927,
+      "learning_rate": 4.358008224267245e-06,
+      "loss": 0.4005,
+      "step": 198
+    },
+    {
+      "epoch": 0.543344709897611,
+      "grad_norm": 0.16464541852474213,
+      "learning_rate": 4.3154697103826235e-06,
+      "loss": 0.4058,
+      "step": 199
+    },
+    {
+      "epoch": 0.5460750853242321,
+      "grad_norm": 0.15310809016227722,
+      "learning_rate": 4.272981630981551e-06,
+      "loss": 0.4049,
+      "step": 200
+    },
+    {
+      "epoch": 0.5488054607508532,
+      "grad_norm": 0.16250354051589966,
+      "learning_rate": 4.230547116479691e-06,
+      "loss": 0.3779,
+      "step": 201
+    },
+    {
+      "epoch": 0.5515358361774744,
+      "grad_norm": 0.14419779181480408,
+      "learning_rate": 4.1881692933461835e-06,
+      "loss": 0.4129,
+      "step": 202
+    },
+    {
+      "epoch": 0.5542662116040956,
+      "grad_norm": 0.1601477712392807,
+      "learning_rate": 4.14585128387328e-06,
+      "loss": 0.3993,
+      "step": 203
+    },
+    {
+      "epoch": 0.5569965870307167,
+      "grad_norm": 0.16939853131771088,
+      "learning_rate": 4.103596205946323e-06,
+      "loss": 0.3928,
+      "step": 204
+    },
+    {
+      "epoch": 0.5597269624573379,
+      "grad_norm": 0.14936766028404236,
+      "learning_rate": 4.061407172814008e-06,
+      "loss": 0.4118,
+      "step": 205
+    },
+    {
+      "epoch": 0.562457337883959,
+      "grad_norm": 0.1553383320569992,
+      "learning_rate": 4.019287292859016e-06,
+      "loss": 0.4031,
+      "step": 206
+    },
+    {
+      "epoch": 0.5651877133105802,
+      "grad_norm": 0.1629059761762619,
+      "learning_rate": 3.977239669368998e-06,
+      "loss": 0.4143,
+      "step": 207
+    },
+    {
+      "epoch": 0.5679180887372014,
+      "grad_norm": 0.147048220038414,
+      "learning_rate": 3.9352674003079225e-06,
+      "loss": 0.3907,
+      "step": 208
+    },
+    {
+      "epoch": 0.5706484641638225,
+      "grad_norm": 0.1578659862279892,
+      "learning_rate": 3.893373578087838e-06,
+      "loss": 0.4011,
+      "step": 209
+    },
+    {
+      "epoch": 0.5733788395904437,
+      "grad_norm": 0.15005314350128174,
+      "learning_rate": 3.851561289341023e-06,
+      "loss": 0.4038,
+      "step": 210
+    },
+    {
+      "epoch": 0.5761092150170648,
+      "grad_norm": 0.16171501576900482,
+      "learning_rate": 3.8098336146925728e-06,
+      "loss": 0.395,
+      "step": 211
+    },
+    {
+      "epoch": 0.578839590443686,
+      "grad_norm": 0.17219065129756927,
+      "learning_rate": 3.768193628533427e-06,
+      "loss": 0.4064,
+      "step": 212
+    },
+    {
+      "epoch": 0.5815699658703072,
+      "grad_norm": 0.14859041571617126,
+      "learning_rate": 3.726644398793857e-06,
+      "loss": 0.4054,
+      "step": 213
+    },
+    {
+      "epoch": 0.5843003412969283,
+      "grad_norm": 0.16669155657291412,
+      "learning_rate": 3.685188986717427e-06,
+      "loss": 0.4145,
+      "step": 214
+    },
+    {
+      "epoch": 0.5870307167235495,
+      "grad_norm": 0.16787604987621307,
+      "learning_rate": 3.6438304466354503e-06,
+      "loss": 0.4329,
+      "step": 215
+    },
+    {
+      "epoch": 0.5897610921501707,
+      "grad_norm": 0.17759054899215698,
+      "learning_rate": 3.6025718257419532e-06,
+      "loss": 0.4238,
+      "step": 216
+    },
+    {
+      "epoch": 0.5924914675767918,
+      "grad_norm": 0.15464290976524353,
+      "learning_rate": 3.5614161638691657e-06,
+      "loss": 0.4122,
+      "step": 217
+    },
+    {
+      "epoch": 0.595221843003413,
+      "grad_norm": 0.146434485912323,
+      "learning_rate": 3.520366493263554e-06,
+      "loss": 0.4004,
+      "step": 218
+    },
+    {
+      "epoch": 0.5979522184300341,
+      "grad_norm": 0.15158678591251373,
+      "learning_rate": 3.4794258383624115e-06,
+      "loss": 0.4246,
+      "step": 219
+    },
+    {
+      "epoch": 0.6006825938566553,
+      "grad_norm": 0.17705509066581726,
+      "learning_rate": 3.4385972155710274e-06,
+      "loss": 0.4105,
+      "step": 220
+    },
+    {
+      "epoch": 0.6034129692832765,
+      "grad_norm": 0.15027230978012085,
+      "learning_rate": 3.3978836330404453e-06,
+      "loss": 0.4264,
+      "step": 221
+    },
+    {
+      "epoch": 0.6061433447098976,
+      "grad_norm": 0.14981985092163086,
+      "learning_rate": 3.3572880904458267e-06,
+      "loss": 0.4188,
+      "step": 222
+    },
+    {
+      "epoch": 0.6088737201365187,
+      "grad_norm": 0.15152880549430847,
+      "learning_rate": 3.3168135787654493e-06,
+      "loss": 0.3935,
+      "step": 223
+    },
+    {
+      "epoch": 0.6116040955631399,
+      "grad_norm": 0.15876388549804688,
+      "learning_rate": 3.2764630800603314e-06,
+      "loss": 0.4193,
+      "step": 224
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 0.15047837793827057,
+      "learning_rate": 3.236239567254526e-06,
+      "loss": 0.3916,
+      "step": 225
+    },
+    {
+      "epoch": 0.6170648464163823,
+      "grad_norm": 0.15240547060966492,
+      "learning_rate": 3.1961460039160842e-06,
+      "loss": 0.4187,
+      "step": 226
+    },
+    {
+      "epoch": 0.6197952218430034,
+      "grad_norm": 0.15835705399513245,
+      "learning_rate": 3.1561853440387e-06,
+      "loss": 0.4008,
+      "step": 227
+    },
+    {
+      "epoch": 0.6225255972696245,
+      "grad_norm": 0.16235880553722382,
+      "learning_rate": 3.116360531824074e-06,
+      "loss": 0.4239,
+      "step": 228
+    },
+    {
+      "epoch": 0.6252559726962458,
+      "grad_norm": 0.16306978464126587,
+      "learning_rate": 3.076674501464994e-06,
+      "loss": 0.4139,
+      "step": 229
+    },
+    {
+      "epoch": 0.6279863481228669,
+      "grad_norm": 0.14479714632034302,
+      "learning_rate": 3.0371301769291417e-06,
+      "loss": 0.4157,
+      "step": 230
+    },
+    {
+      "epoch": 0.630716723549488,
+      "grad_norm": 0.1663469821214676,
+      "learning_rate": 2.997730471743667e-06,
+      "loss": 0.4301,
+      "step": 231
+    },
+    {
+      "epoch": 0.6334470989761092,
+      "grad_norm": 0.1759214997291565,
+      "learning_rate": 2.958478288780533e-06,
+      "loss": 0.3993,
+      "step": 232
+    },
+    {
+      "epoch": 0.6361774744027304,
+      "grad_norm": 0.1472492516040802,
+      "learning_rate": 2.919376520042628e-06,
+      "loss": 0.3998,
+      "step": 233
+    },
+    {
+      "epoch": 0.6389078498293516,
+      "grad_norm": 0.14618809521198273,
+      "learning_rate": 2.880428046450697e-06,
+      "loss": 0.3921,
+      "step": 234
+    },
+    {
+      "epoch": 0.6416382252559727,
+      "grad_norm": 0.1660156548023224,
+      "learning_rate": 2.8416357376310823e-06,
+      "loss": 0.4095,
+      "step": 235
+    },
+    {
+      "epoch": 0.6443686006825938,
+      "grad_norm": 0.1544540971517563,
+      "learning_rate": 2.8030024517042907e-06,
+      "loss": 0.4112,
+      "step": 236
+    },
+    {
+      "epoch": 0.647098976109215,
+      "grad_norm": 0.1531461477279663,
+      "learning_rate": 2.7645310350744296e-06,
+      "loss": 0.4079,
+      "step": 237
+    },
+    {
+      "epoch": 0.6498293515358362,
+      "grad_norm": 0.16143448650836945,
+      "learning_rate": 2.7262243222194728e-06,
+      "loss": 0.4088,
+      "step": 238
+    },
+    {
+      "epoch": 0.6525597269624573,
+      "grad_norm": 0.1632911115884781,
+      "learning_rate": 2.6880851354824277e-06,
+      "loss": 0.406,
+      "step": 239
+    },
+    {
+      "epoch": 0.6552901023890785,
+      "grad_norm": 0.15283940732479095,
+      "learning_rate": 2.6501162848634023e-06,
+      "loss": 0.3922,
+      "step": 240
+    },
+    {
+      "epoch": 0.6580204778156996,
+      "grad_norm": 0.15318641066551208,
+      "learning_rate": 2.6123205678125597e-06,
+      "loss": 0.39,
+      "step": 241
+    },
+    {
+      "epoch": 0.6607508532423209,
+      "grad_norm": 0.15297549962997437,
+      "learning_rate": 2.57470076902402e-06,
+      "loss": 0.3991,
+      "step": 242
+    },
+    {
+      "epoch": 0.663481228668942,
+      "grad_norm": 0.1510440558195114,
+      "learning_rate": 2.537259660230679e-06,
+      "loss": 0.418,
+      "step": 243
+    },
+    {
+      "epoch": 0.6662116040955631,
+      "grad_norm": 0.14892160892486572,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.3863,
+      "step": 244
+    },
+    {
+      "epoch": 0.6689419795221843,
+      "grad_norm": 0.1641772985458374,
+      "learning_rate": 2.462924533530774e-06,
+      "loss": 0.4333,
+      "step": 245
+    },
+    {
+      "epoch": 0.6716723549488055,
+      "grad_norm": 0.15933027863502502,
+      "learning_rate": 2.426035992450848e-06,
+      "loss": 0.4064,
+      "step": 246
+    },
+    {
+      "epoch": 0.6744027303754266,
+      "grad_norm": 0.14534929394721985,
+      "learning_rate": 2.3893370946158758e-06,
+      "loss": 0.404,
+      "step": 247
+    },
+    {
+      "epoch": 0.6771331058020478,
+      "grad_norm": 0.1527319997549057,
+      "learning_rate": 2.3528305439090744e-06,
+      "loss": 0.4081,
+      "step": 248
+    },
+    {
+      "epoch": 0.6798634812286689,
+      "grad_norm": 0.15615414083003998,
+      "learning_rate": 2.316519030041998e-06,
+      "loss": 0.4067,
+      "step": 249
+    },
+    {
+      "epoch": 0.6825938566552902,
+      "grad_norm": 0.17054639756679535,
+      "learning_rate": 2.280405228356377e-06,
+      "loss": 0.4088,
+      "step": 250
+    },
+    {
+      "epoch": 0.6853242320819113,
+      "grad_norm": 0.163183331489563,
+      "learning_rate": 2.2444917996270003e-06,
+      "loss": 0.4131,
+      "step": 251
+    },
+    {
+      "epoch": 0.6880546075085324,
+      "grad_norm": 0.15478871762752533,
+      "learning_rate": 2.2087813898656775e-06,
+      "loss": 0.4161,
+      "step": 252
+    },
+    {
+      "epoch": 0.6907849829351536,
+      "grad_norm": 0.15877461433410645,
+      "learning_rate": 2.173276630126287e-06,
+      "loss": 0.3991,
+      "step": 253
+    },
+    {
+      "epoch": 0.6935153583617747,
+      "grad_norm": 0.16762347519397736,
+      "learning_rate": 2.137980136310926e-06,
+      "loss": 0.4094,
+      "step": 254
+    },
+    {
+      "epoch": 0.6962457337883959,
+      "grad_norm": 0.1578551083803177,
+      "learning_rate": 2.102894508977182e-06,
+      "loss": 0.4108,
+      "step": 255
+    },
+    {
+      "epoch": 0.6989761092150171,
+      "grad_norm": 0.17313554883003235,
+      "learning_rate": 2.0680223331465223e-06,
+      "loss": 0.4112,
+      "step": 256
+    },
+    {
+      "epoch": 0.7017064846416382,
+      "grad_norm": 0.1474330574274063,
+      "learning_rate": 2.033366178113841e-06,
+      "loss": 0.3995,
+      "step": 257
+    },
+    {
+      "epoch": 0.7044368600682593,
+      "grad_norm": 0.15970253944396973,
+      "learning_rate": 1.9989285972581595e-06,
+      "loss": 0.3998,
+      "step": 258
+    },
+    {
+      "epoch": 0.7071672354948806,
+      "grad_norm": 0.1546693742275238,
+      "learning_rate": 1.9647121278544996e-06,
+      "loss": 0.3908,
+      "step": 259
+    },
+    {
+      "epoch": 0.7098976109215017,
+      "grad_norm": 0.15894074738025665,
+      "learning_rate": 1.93071929088694e-06,
+      "loss": 0.4179,
+      "step": 260
+    },
+    {
+      "epoch": 0.7126279863481229,
+      "grad_norm": 0.15951929986476898,
+      "learning_rate": 1.896952590862886e-06,
+      "loss": 0.407,
+      "step": 261
+    },
+    {
+      "epoch": 0.715358361774744,
+      "grad_norm": 0.145669087767601,
+      "learning_rate": 1.8634145156285311e-06,
+      "loss": 0.3863,
+      "step": 262
+    },
+    {
+      "epoch": 0.7180887372013652,
+      "grad_norm": 0.16664068400859833,
+      "learning_rate": 1.8301075361855674e-06,
+      "loss": 0.3965,
+      "step": 263
+    },
+    {
+      "epoch": 0.7208191126279864,
+      "grad_norm": 0.15179961919784546,
+      "learning_rate": 1.7970341065091246e-06,
+      "loss": 0.3872,
+      "step": 264
+    },
+    {
+      "epoch": 0.7235494880546075,
+      "grad_norm": 0.16116613149642944,
+      "learning_rate": 1.7641966633669705e-06,
+      "loss": 0.4082,
+      "step": 265
+    },
+    {
+      "epoch": 0.7262798634812286,
+      "grad_norm": 0.15431508421897888,
+      "learning_rate": 1.7315976261399698e-06,
+      "loss": 0.4136,
+      "step": 266
+    },
+    {
+      "epoch": 0.7290102389078499,
+      "grad_norm": 0.1545833945274353,
+      "learning_rate": 1.699239396643841e-06,
+      "loss": 0.3969,
+      "step": 267
+    },
+    {
+      "epoch": 0.731740614334471,
+      "grad_norm": 0.1713000386953354,
+      "learning_rate": 1.667124358952184e-06,
+      "loss": 0.4188,
+      "step": 268
+    },
+    {
+      "epoch": 0.7344709897610922,
+      "grad_norm": 0.16345979273319244,
+      "learning_rate": 1.6352548792208356e-06,
+      "loss": 0.4029,
+      "step": 269
+    },
+    {
+      "epoch": 0.7372013651877133,
+      "grad_norm": 0.14592435956001282,
+      "learning_rate": 1.6036333055135345e-06,
+      "loss": 0.4044,
+      "step": 270
+    },
+    {
+      "epoch": 0.7399317406143344,
+      "grad_norm": 0.1973186582326889,
+      "learning_rate": 1.572261967628923e-06,
+      "loss": 0.3998,
+      "step": 271
+    },
+    {
+      "epoch": 0.7426621160409557,
+      "grad_norm": 0.15132401883602142,
+      "learning_rate": 1.541143176928891e-06,
+      "loss": 0.3928,
+      "step": 272
+    },
+    {
+      "epoch": 0.7453924914675768,
+      "grad_norm": 0.1545684039592743,
+      "learning_rate": 1.5102792261682813e-06,
+      "loss": 0.3963,
+      "step": 273
+    },
+    {
+      "epoch": 0.7481228668941979,
+      "grad_norm": 0.1502438336610794,
+      "learning_rate": 1.4796723893259712e-06,
+      "loss": 0.4006,
+      "step": 274
+    },
+    {
+      "epoch": 0.7508532423208191,
+      "grad_norm": 0.15633085370063782,
+      "learning_rate": 1.4493249214373224e-06,
+      "loss": 0.3979,
+      "step": 275
+    },
+    {
+      "epoch": 0.7535836177474403,
+      "grad_norm": 0.15326417982578278,
+      "learning_rate": 1.4192390584280347e-06,
+      "loss": 0.4017,
+      "step": 276
+    },
+    {
+      "epoch": 0.7563139931740614,
+      "grad_norm": 0.1504485011100769,
+      "learning_rate": 1.3894170169494192e-06,
+      "loss": 0.4146,
+      "step": 277
+    },
+    {
+      "epoch": 0.7590443686006826,
+      "grad_norm": 0.1470741629600525,
+      "learning_rate": 1.3598609942150765e-06,
+      "loss": 0.3954,
+      "step": 278
+    },
+    {
+      "epoch": 0.7617747440273037,
+      "grad_norm": 0.16345715522766113,
+      "learning_rate": 1.330573167839005e-06,
+      "loss": 0.409,
+      "step": 279
+    },
+    {
+      "epoch": 0.764505119453925,
+      "grad_norm": 0.15342997014522552,
+      "learning_rate": 1.3015556956751669e-06,
+      "loss": 0.4002,
+      "step": 280
+    },
+    {
+      "epoch": 0.7672354948805461,
+      "grad_norm": 0.1575509011745453,
+      "learning_rate": 1.2728107156585e-06,
+      "loss": 0.4176,
+      "step": 281
+    },
+    {
+      "epoch": 0.7699658703071672,
+      "grad_norm": 0.1618194580078125,
+      "learning_rate": 1.2443403456474017e-06,
+      "loss": 0.3958,
+      "step": 282
+    },
+    {
+      "epoch": 0.7726962457337884,
+      "grad_norm": 0.15315888822078705,
+      "learning_rate": 1.2161466832676888e-06,
+      "loss": 0.4045,
+      "step": 283
+    },
+    {
+      "epoch": 0.7754266211604095,
+      "grad_norm": 0.14545629918575287,
+      "learning_rate": 1.188231805758049e-06,
+      "loss": 0.3981,
+      "step": 284
+    },
+    {
+      "epoch": 0.7781569965870307,
+      "grad_norm": 0.17285780608654022,
+      "learning_rate": 1.1605977698170001e-06,
+      "loss": 0.416,
+      "step": 285
+    },
+    {
+      "epoch": 0.7808873720136519,
+      "grad_norm": 0.15523703396320343,
+      "learning_rate": 1.1332466114513512e-06,
+      "loss": 0.4163,
+      "step": 286
+    },
+    {
+      "epoch": 0.783617747440273,
+      "grad_norm": 0.15426713228225708,
+      "learning_rate": 1.1061803458261977e-06,
+      "loss": 0.405,
+      "step": 287
+    },
+    {
+      "epoch": 0.7863481228668942,
+      "grad_norm": 0.15107548236846924,
+      "learning_rate": 1.0794009671164484e-06,
+      "loss": 0.3818,
+      "step": 288
+    },
+    {
+      "epoch": 0.7890784982935154,
+      "grad_norm": 0.15870976448059082,
+      "learning_rate": 1.0529104483599023e-06,
+      "loss": 0.4044,
+      "step": 289
+    },
+    {
+      "epoch": 0.7918088737201365,
+      "grad_norm": 0.16166147589683533,
+      "learning_rate": 1.0267107413118743e-06,
+      "loss": 0.4029,
+      "step": 290
+    },
+    {
+      "epoch": 0.7945392491467577,
+      "grad_norm": 0.15707789361476898,
+      "learning_rate": 1.0008037763014033e-06,
+      "loss": 0.3903,
+      "step": 291
+    },
+    {
+      "epoch": 0.7972696245733788,
+      "grad_norm": 0.17786303162574768,
+      "learning_rate": 9.751914620890208e-07,
+      "loss": 0.4083,
+      "step": 292
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.153977632522583,
+      "learning_rate": 9.498756857261243e-07,
+      "loss": 0.4119,
+      "step": 293
+    },
+    {
+      "epoch": 0.8027303754266212,
+      "grad_norm": 0.15868696570396423,
+      "learning_rate": 9.248583124159438e-07,
+      "loss": 0.4064,
+      "step": 294
+    },
+    {
+      "epoch": 0.8054607508532423,
+      "grad_norm": 0.16338956356048584,
+      "learning_rate": 9.00141185376115e-07,
+      "loss": 0.4042,
+      "step": 295
+    },
+    {
+      "epoch": 0.8081911262798634,
+      "grad_norm": 0.14950022101402283,
+      "learning_rate": 8.757261257028776e-07,
+      "loss": 0.396,
+      "step": 296
+    },
+    {
+      "epoch": 0.8109215017064847,
+      "grad_norm": 0.15251553058624268,
+      "learning_rate": 8.516149322369055e-07,
+      "loss": 0.4055,
+      "step": 297
+    },
+    {
+      "epoch": 0.8136518771331058,
+      "grad_norm": 0.16309964656829834,
+      "learning_rate": 8.278093814307637e-07,
+      "loss": 0.3992,
+      "step": 298
+    },
+    {
+      "epoch": 0.816382252559727,
+      "grad_norm": 0.1547779142856598,
+      "learning_rate": 8.043112272180309e-07,
+      "loss": 0.3959,
+      "step": 299
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.16333834826946259,
+      "learning_rate": 7.811222008840719e-07,
+      "loss": 0.401,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.584768638870356e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2894cbb412e8163f51ee66bc37edad64bb67e6527266f7add94fd1e6f4dbcfc6
+size 6968

checkpoint-366/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models/DeepSeek-R1-Distill-Qwen-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-366/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/DeepSeek-R1-Distill-Qwen-7B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-366/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d953bcecd11620229236245187a31cde5d30d3fb85b1840f178c0b74d166e0
+size 161496088

checkpoint-366/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-366/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

checkpoint-366/tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{%- if messages|length == 1 and messages[0]['role'] == 'assistant' -%}{%- if messages[0]['content'] is not none -%}{{'<｜Assistant｜>' + messages[0]['content'] + '<｜end▁of▁sentence｜>'}}{%- endif -%}{%- else -%}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{{'<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor -%}{%- endif -%}{% if add_generation_prompt %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-366/trainer_state.json

@@ -0,0 +1,2595 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993174061433447,
+  "eval_steps": 500,
+  "global_step": 366,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027303754266211604,
+      "grad_norm": 3.856764554977417,
+      "learning_rate": 9.999815806238551e-06,
+      "loss": 0.5425,
+      "step": 1
+    },
+    {
+      "epoch": 0.005460750853242321,
+      "grad_norm": 3.6394715309143066,
+      "learning_rate": 9.999263238525135e-06,
+      "loss": 0.5588,
+      "step": 2
+    },
+    {
+      "epoch": 0.008191126279863481,
+      "grad_norm": 3.228754758834839,
+      "learning_rate": 9.998342337571566e-06,
+      "loss": 0.5072,
+      "step": 3
+    },
+    {
+      "epoch": 0.010921501706484642,
+      "grad_norm": 2.7734687328338623,
+      "learning_rate": 9.997053171227527e-06,
+      "loss": 0.524,
+      "step": 4
+    },
+    {
+      "epoch": 0.013651877133105802,
+      "grad_norm": 2.6146395206451416,
+      "learning_rate": 9.995395834475578e-06,
+      "loss": 0.5013,
+      "step": 5
+    },
+    {
+      "epoch": 0.016382252559726963,
+      "grad_norm": 2.3134093284606934,
+      "learning_rate": 9.993370449424153e-06,
+      "loss": 0.5021,
+      "step": 6
+    },
+    {
+      "epoch": 0.01911262798634812,
+      "grad_norm": 2.46028995513916,
+      "learning_rate": 9.990977165298571e-06,
+      "loss": 0.5048,
+      "step": 7
+    },
+    {
+      "epoch": 0.021843003412969283,
+      "grad_norm": 2.1209499835968018,
+      "learning_rate": 9.988216158430033e-06,
+      "loss": 0.4865,
+      "step": 8
+    },
+    {
+      "epoch": 0.024573378839590442,
+      "grad_norm": 2.0378663539886475,
+      "learning_rate": 9.985087632242634e-06,
+      "loss": 0.5033,
+      "step": 9
+    },
+    {
+      "epoch": 0.027303754266211604,
+      "grad_norm": 1.8533931970596313,
+      "learning_rate": 9.981591817238379e-06,
+      "loss": 0.4731,
+      "step": 10
+    },
+    {
+      "epoch": 0.030034129692832763,
+      "grad_norm": 1.7073378562927246,
+      "learning_rate": 9.977728970980193e-06,
+      "loss": 0.4592,
+      "step": 11
+    },
+    {
+      "epoch": 0.032764505119453925,
+      "grad_norm": 1.763203501701355,
+      "learning_rate": 9.973499378072947e-06,
+      "loss": 0.4569,
+      "step": 12
+    },
+    {
+      "epoch": 0.03549488054607509,
+      "grad_norm": 1.2629003524780273,
+      "learning_rate": 9.968903350142494e-06,
+      "loss": 0.4364,
+      "step": 13
+    },
+    {
+      "epoch": 0.03822525597269624,
+      "grad_norm": 1.345859408378601,
+      "learning_rate": 9.9639412258127e-06,
+      "loss": 0.4737,
+      "step": 14
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 1.291548490524292,
+      "learning_rate": 9.958613370680507e-06,
+      "loss": 0.4504,
+      "step": 15
+    },
+    {
+      "epoch": 0.04368600682593857,
+      "grad_norm": 1.3444461822509766,
+      "learning_rate": 9.952920177288985e-06,
+      "loss": 0.457,
+      "step": 16
+    },
+    {
+      "epoch": 0.04641638225255973,
+      "grad_norm": 1.5857586860656738,
+      "learning_rate": 9.946862065098415e-06,
+      "loss": 0.4696,
+      "step": 17
+    },
+    {
+      "epoch": 0.049146757679180884,
+      "grad_norm": 1.1109745502471924,
+      "learning_rate": 9.940439480455386e-06,
+      "loss": 0.4417,
+      "step": 18
+    },
+    {
+      "epoch": 0.05187713310580205,
+      "grad_norm": 1.1297810077667236,
+      "learning_rate": 9.933652896559907e-06,
+      "loss": 0.4463,
+      "step": 19
+    },
+    {
+      "epoch": 0.05460750853242321,
+      "grad_norm": 1.0981742143630981,
+      "learning_rate": 9.926502813430545e-06,
+      "loss": 0.4499,
+      "step": 20
+    },
+    {
+      "epoch": 0.05733788395904437,
+      "grad_norm": 1.1592185497283936,
+      "learning_rate": 9.918989757867584e-06,
+      "loss": 0.447,
+      "step": 21
+    },
+    {
+      "epoch": 0.060068259385665526,
+      "grad_norm": 1.0812605619430542,
+      "learning_rate": 9.911114283414204e-06,
+      "loss": 0.4638,
+      "step": 22
+    },
+    {
+      "epoch": 0.06279863481228669,
+      "grad_norm": 0.774226188659668,
+      "learning_rate": 9.902876970315715e-06,
+      "loss": 0.4439,
+      "step": 23
+    },
+    {
+      "epoch": 0.06552901023890785,
+      "grad_norm": 0.7117806673049927,
+      "learning_rate": 9.89427842547679e-06,
+      "loss": 0.4424,
+      "step": 24
+    },
+    {
+      "epoch": 0.06825938566552901,
+      "grad_norm": 0.7732372283935547,
+      "learning_rate": 9.885319282416755e-06,
+      "loss": 0.4494,
+      "step": 25
+    },
+    {
+      "epoch": 0.07098976109215017,
+      "grad_norm": 0.7167857885360718,
+      "learning_rate": 9.876000201222912e-06,
+      "loss": 0.4514,
+      "step": 26
+    },
+    {
+      "epoch": 0.07372013651877134,
+      "grad_norm": 0.7761046290397644,
+      "learning_rate": 9.866321868501914e-06,
+      "loss": 0.462,
+      "step": 27
+    },
+    {
+      "epoch": 0.07645051194539249,
+      "grad_norm": 0.5660157203674316,
+      "learning_rate": 9.856284997329158e-06,
+      "loss": 0.4455,
+      "step": 28
+    },
+    {
+      "epoch": 0.07918088737201365,
+      "grad_norm": 0.5861382484436035,
+      "learning_rate": 9.845890327196269e-06,
+      "loss": 0.4416,
+      "step": 29
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 0.7201432585716248,
+      "learning_rate": 9.835138623956603e-06,
+      "loss": 0.4209,
+      "step": 30
+    },
+    {
+      "epoch": 0.08464163822525597,
+      "grad_norm": 0.8803044557571411,
+      "learning_rate": 9.824030679768824e-06,
+      "loss": 0.4276,
+      "step": 31
+    },
+    {
+      "epoch": 0.08737201365187713,
+      "grad_norm": 0.7925510406494141,
+      "learning_rate": 9.812567313038542e-06,
+      "loss": 0.4473,
+      "step": 32
+    },
+    {
+      "epoch": 0.0901023890784983,
+      "grad_norm": 0.9926882982254028,
+      "learning_rate": 9.80074936835801e-06,
+      "loss": 0.4398,
+      "step": 33
+    },
+    {
+      "epoch": 0.09283276450511946,
+      "grad_norm": 0.8362368941307068,
+      "learning_rate": 9.788577716443903e-06,
+      "loss": 0.4347,
+      "step": 34
+    },
+    {
+      "epoch": 0.09556313993174062,
+      "grad_norm": 0.8301376104354858,
+      "learning_rate": 9.77605325407316e-06,
+      "loss": 0.4684,
+      "step": 35
+    },
+    {
+      "epoch": 0.09829351535836177,
+      "grad_norm": 0.7239497900009155,
+      "learning_rate": 9.763176904016914e-06,
+      "loss": 0.4686,
+      "step": 36
+    },
+    {
+      "epoch": 0.10102389078498293,
+      "grad_norm": 0.6108490824699402,
+      "learning_rate": 9.749949614972507e-06,
+      "loss": 0.431,
+      "step": 37
+    },
+    {
+      "epoch": 0.1037542662116041,
+      "grad_norm": 0.5505651235580444,
+      "learning_rate": 9.736372361493584e-06,
+      "loss": 0.4383,
+      "step": 38
+    },
+    {
+      "epoch": 0.10648464163822526,
+      "grad_norm": 0.5642620325088501,
+      "learning_rate": 9.722446143918307e-06,
+      "loss": 0.4249,
+      "step": 39
+    },
+    {
+      "epoch": 0.10921501706484642,
+      "grad_norm": 0.4733835458755493,
+      "learning_rate": 9.70817198829563e-06,
+      "loss": 0.4404,
+      "step": 40
+    },
+    {
+      "epoch": 0.11194539249146758,
+      "grad_norm": 0.43274644017219543,
+      "learning_rate": 9.693550946309721e-06,
+      "loss": 0.428,
+      "step": 41
+    },
+    {
+      "epoch": 0.11467576791808874,
+      "grad_norm": 0.45345625281333923,
+      "learning_rate": 9.678584095202468e-06,
+      "loss": 0.4559,
+      "step": 42
+    },
+    {
+      "epoch": 0.1174061433447099,
+      "grad_norm": 0.3903965353965759,
+      "learning_rate": 9.663272537694112e-06,
+      "loss": 0.4419,
+      "step": 43
+    },
+    {
+      "epoch": 0.12013651877133105,
+      "grad_norm": 0.5206829905509949,
+      "learning_rate": 9.647617401902003e-06,
+      "loss": 0.4366,
+      "step": 44
+    },
+    {
+      "epoch": 0.12286689419795221,
+      "grad_norm": 0.38311880826950073,
+      "learning_rate": 9.631619841257477e-06,
+      "loss": 0.4289,
+      "step": 45
+    },
+    {
+      "epoch": 0.12559726962457338,
+      "grad_norm": 0.4225156903266907,
+      "learning_rate": 9.615281034420882e-06,
+      "loss": 0.4215,
+      "step": 46
+    },
+    {
+      "epoch": 0.12832764505119454,
+      "grad_norm": 0.4255654513835907,
+      "learning_rate": 9.598602185194733e-06,
+      "loss": 0.4247,
+      "step": 47
+    },
+    {
+      "epoch": 0.1310580204778157,
+      "grad_norm": 0.4347112774848938,
+      "learning_rate": 9.581584522435025e-06,
+      "loss": 0.427,
+      "step": 48
+    },
+    {
+      "epoch": 0.13378839590443686,
+      "grad_norm": 0.34471118450164795,
+      "learning_rate": 9.564229299960679e-06,
+      "loss": 0.421,
+      "step": 49
+    },
+    {
+      "epoch": 0.13651877133105803,
+      "grad_norm": 0.43423381447792053,
+      "learning_rate": 9.54653779646118e-06,
+      "loss": 0.4322,
+      "step": 50
+    },
+    {
+      "epoch": 0.1392491467576792,
+      "grad_norm": 0.4541296064853668,
+      "learning_rate": 9.528511315402358e-06,
+      "loss": 0.4212,
+      "step": 51
+    },
+    {
+      "epoch": 0.14197952218430035,
+      "grad_norm": 0.29571640491485596,
+      "learning_rate": 9.510151184930354e-06,
+      "loss": 0.4312,
+      "step": 52
+    },
+    {
+      "epoch": 0.1447098976109215,
+      "grad_norm": 0.30192604660987854,
+      "learning_rate": 9.491458757773766e-06,
+      "loss": 0.4328,
+      "step": 53
+    },
+    {
+      "epoch": 0.14744027303754267,
+      "grad_norm": 0.24025903642177582,
+      "learning_rate": 9.472435411143979e-06,
+      "loss": 0.4214,
+      "step": 54
+    },
+    {
+      "epoch": 0.15017064846416384,
+      "grad_norm": 0.3551096022129059,
+      "learning_rate": 9.453082546633704e-06,
+      "loss": 0.4232,
+      "step": 55
+    },
+    {
+      "epoch": 0.15290102389078497,
+      "grad_norm": 0.2226678431034088,
+      "learning_rate": 9.433401590113702e-06,
+      "loss": 0.4332,
+      "step": 56
+    },
+    {
+      "epoch": 0.15563139931740613,
+      "grad_norm": 0.21858179569244385,
+      "learning_rate": 9.413393991627737e-06,
+      "loss": 0.418,
+      "step": 57
+    },
+    {
+      "epoch": 0.1583617747440273,
+      "grad_norm": 0.22533869743347168,
+      "learning_rate": 9.393061225285743e-06,
+      "loss": 0.4361,
+      "step": 58
+    },
+    {
+      "epoch": 0.16109215017064846,
+      "grad_norm": 0.21001799404621124,
+      "learning_rate": 9.372404789155199e-06,
+      "loss": 0.4187,
+      "step": 59
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.20293086767196655,
+      "learning_rate": 9.351426205150778e-06,
+      "loss": 0.4252,
+      "step": 60
+    },
+    {
+      "epoch": 0.16655290102389078,
+      "grad_norm": 0.22262097895145416,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.4442,
+      "step": 61
+    },
+    {
+      "epoch": 0.16928327645051194,
+      "grad_norm": 0.21581031382083893,
+      "learning_rate": 9.30850879974034e-06,
+      "loss": 0.4233,
+      "step": 62
+    },
+    {
+      "epoch": 0.1720136518771331,
+      "grad_norm": 0.2510773837566376,
+      "learning_rate": 9.286573140381663e-06,
+      "loss": 0.4126,
+      "step": 63
+    },
+    {
+      "epoch": 0.17474402730375427,
+      "grad_norm": 0.22764866054058075,
+      "learning_rate": 9.2643216570108e-06,
+      "loss": 0.4435,
+      "step": 64
+    },
+    {
+      "epoch": 0.17747440273037543,
+      "grad_norm": 0.2921380400657654,
+      "learning_rate": 9.24175598906152e-06,
+      "loss": 0.4006,
+      "step": 65
+    },
+    {
+      "epoch": 0.1802047781569966,
+      "grad_norm": 0.2642498314380646,
+      "learning_rate": 9.218877799115929e-06,
+      "loss": 0.4224,
+      "step": 66
+    },
+    {
+      "epoch": 0.18293515358361775,
+      "grad_norm": 0.2313549965620041,
+      "learning_rate": 9.19568877278197e-06,
+      "loss": 0.413,
+      "step": 67
+    },
+    {
+      "epoch": 0.18566552901023892,
+      "grad_norm": 0.2201680839061737,
+      "learning_rate": 9.172190618569236e-06,
+      "loss": 0.4278,
+      "step": 68
+    },
+    {
+      "epoch": 0.18839590443686008,
+      "grad_norm": 0.2556556463241577,
+      "learning_rate": 9.148385067763094e-06,
+      "loss": 0.4216,
+      "step": 69
+    },
+    {
+      "epoch": 0.19112627986348124,
+      "grad_norm": 0.238591730594635,
+      "learning_rate": 9.124273874297123e-06,
+      "loss": 0.4217,
+      "step": 70
+    },
+    {
+      "epoch": 0.19385665529010238,
+      "grad_norm": 0.2658149302005768,
+      "learning_rate": 9.099858814623887e-06,
+      "loss": 0.4159,
+      "step": 71
+    },
+    {
+      "epoch": 0.19658703071672354,
+      "grad_norm": 0.26856058835983276,
+      "learning_rate": 9.075141687584056e-06,
+      "loss": 0.4285,
+      "step": 72
+    },
+    {
+      "epoch": 0.1993174061433447,
+      "grad_norm": 0.1793709248304367,
+      "learning_rate": 9.050124314273876e-06,
+      "loss": 0.4255,
+      "step": 73
+    },
+    {
+      "epoch": 0.20204778156996586,
+      "grad_norm": 0.1868457794189453,
+      "learning_rate": 9.024808537910981e-06,
+      "loss": 0.417,
+      "step": 74
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.19721131026744843,
+      "learning_rate": 8.999196223698599e-06,
+      "loss": 0.4234,
+      "step": 75
+    },
+    {
+      "epoch": 0.2075085324232082,
+      "grad_norm": 0.1849862039089203,
+      "learning_rate": 8.973289258688125e-06,
+      "loss": 0.3868,
+      "step": 76
+    },
+    {
+      "epoch": 0.21023890784982935,
+      "grad_norm": 0.18427810072898865,
+      "learning_rate": 8.9470895516401e-06,
+      "loss": 0.4205,
+      "step": 77
+    },
+    {
+      "epoch": 0.2129692832764505,
+      "grad_norm": 0.22481605410575867,
+      "learning_rate": 8.920599032883553e-06,
+      "loss": 0.4271,
+      "step": 78
+    },
+    {
+      "epoch": 0.21569965870307167,
+      "grad_norm": 0.18275555968284607,
+      "learning_rate": 8.893819654173804e-06,
+      "loss": 0.4276,
+      "step": 79
+    },
+    {
+      "epoch": 0.21843003412969283,
+      "grad_norm": 0.17510327696800232,
+      "learning_rate": 8.86675338854865e-06,
+      "loss": 0.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.221160409556314,
+      "grad_norm": 0.18124502897262573,
+      "learning_rate": 8.839402230183e-06,
+      "loss": 0.4181,
+      "step": 81
+    },
+    {
+      "epoch": 0.22389078498293516,
+      "grad_norm": 0.1930208057165146,
+      "learning_rate": 8.811768194241951e-06,
+      "loss": 0.4326,
+      "step": 82
+    },
+    {
+      "epoch": 0.22662116040955632,
+      "grad_norm": 0.17881739139556885,
+      "learning_rate": 8.783853316732313e-06,
+      "loss": 0.4227,
+      "step": 83
+    },
+    {
+      "epoch": 0.22935153583617748,
+      "grad_norm": 0.18276868760585785,
+      "learning_rate": 8.755659654352599e-06,
+      "loss": 0.4109,
+      "step": 84
+    },
+    {
+      "epoch": 0.23208191126279865,
+      "grad_norm": 0.1769554764032364,
+      "learning_rate": 8.727189284341501e-06,
+      "loss": 0.4267,
+      "step": 85
+    },
+    {
+      "epoch": 0.2348122866894198,
+      "grad_norm": 0.22149443626403809,
+      "learning_rate": 8.698444304324837e-06,
+      "loss": 0.4236,
+      "step": 86
+    },
+    {
+      "epoch": 0.23754266211604094,
+      "grad_norm": 0.1817912608385086,
+      "learning_rate": 8.669426832160997e-06,
+      "loss": 0.4235,
+      "step": 87
+    },
+    {
+      "epoch": 0.2402730375426621,
+      "grad_norm": 0.23118089139461517,
+      "learning_rate": 8.640139005784924e-06,
+      "loss": 0.4338,
+      "step": 88
+    },
+    {
+      "epoch": 0.24300341296928327,
+      "grad_norm": 0.23663879930973053,
+      "learning_rate": 8.610582983050581e-06,
+      "loss": 0.4239,
+      "step": 89
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.16908958554267883,
+      "learning_rate": 8.580760941571968e-06,
+      "loss": 0.4148,
+      "step": 90
+    },
+    {
+      "epoch": 0.2484641638225256,
+      "grad_norm": 0.23422765731811523,
+      "learning_rate": 8.55067507856268e-06,
+      "loss": 0.4183,
+      "step": 91
+    },
+    {
+      "epoch": 0.25119453924914675,
+      "grad_norm": 0.24864593148231506,
+      "learning_rate": 8.520327610674029e-06,
+      "loss": 0.41,
+      "step": 92
+    },
+    {
+      "epoch": 0.25392491467576794,
+      "grad_norm": 0.20847055315971375,
+      "learning_rate": 8.489720773831717e-06,
+      "loss": 0.4221,
+      "step": 93
+    },
+    {
+      "epoch": 0.2566552901023891,
+      "grad_norm": 0.19055533409118652,
+      "learning_rate": 8.458856823071111e-06,
+      "loss": 0.4191,
+      "step": 94
+    },
+    {
+      "epoch": 0.2593856655290102,
+      "grad_norm": 0.24293097853660583,
+      "learning_rate": 8.427738032371078e-06,
+      "loss": 0.3906,
+      "step": 95
+    },
+    {
+      "epoch": 0.2621160409556314,
+      "grad_norm": 0.23974299430847168,
+      "learning_rate": 8.396366694486466e-06,
+      "loss": 0.4157,
+      "step": 96
+    },
+    {
+      "epoch": 0.26484641638225254,
+      "grad_norm": 0.1998283416032791,
+      "learning_rate": 8.364745120779166e-06,
+      "loss": 0.4054,
+      "step": 97
+    },
+    {
+      "epoch": 0.2675767918088737,
+      "grad_norm": 0.21701572835445404,
+      "learning_rate": 8.332875641047817e-06,
+      "loss": 0.3984,
+      "step": 98
+    },
+    {
+      "epoch": 0.27030716723549486,
+      "grad_norm": 0.18561778962612152,
+      "learning_rate": 8.30076060335616e-06,
+      "loss": 0.4164,
+      "step": 99
+    },
+    {
+      "epoch": 0.27303754266211605,
+      "grad_norm": 0.1797938048839569,
+      "learning_rate": 8.26840237386003e-06,
+      "loss": 0.4339,
+      "step": 100
+    },
+    {
+      "epoch": 0.2757679180887372,
+      "grad_norm": 0.1605861335992813,
+      "learning_rate": 8.235803336633033e-06,
+      "loss": 0.4053,
+      "step": 101
+    },
+    {
+      "epoch": 0.2784982935153584,
+      "grad_norm": 0.1774858683347702,
+      "learning_rate": 8.202965893490877e-06,
+      "loss": 0.4232,
+      "step": 102
+    },
+    {
+      "epoch": 0.2812286689419795,
+      "grad_norm": 0.15541759133338928,
+      "learning_rate": 8.169892463814435e-06,
+      "loss": 0.4208,
+      "step": 103
+    },
+    {
+      "epoch": 0.2839590443686007,
+      "grad_norm": 0.16066958010196686,
+      "learning_rate": 8.136585484371471e-06,
+      "loss": 0.4074,
+      "step": 104
+    },
+    {
+      "epoch": 0.28668941979522183,
+      "grad_norm": 0.1789342761039734,
+      "learning_rate": 8.103047409137114e-06,
+      "loss": 0.4104,
+      "step": 105
+    },
+    {
+      "epoch": 0.289419795221843,
+      "grad_norm": 0.16283057630062103,
+      "learning_rate": 8.06928070911306e-06,
+      "loss": 0.4073,
+      "step": 106
+    },
+    {
+      "epoch": 0.29215017064846416,
+      "grad_norm": 0.17041556537151337,
+      "learning_rate": 8.035287872145502e-06,
+      "loss": 0.4396,
+      "step": 107
+    },
+    {
+      "epoch": 0.29488054607508535,
+      "grad_norm": 0.17072531580924988,
+      "learning_rate": 8.001071402741843e-06,
+      "loss": 0.4297,
+      "step": 108
+    },
+    {
+      "epoch": 0.2976109215017065,
+      "grad_norm": 0.16717186570167542,
+      "learning_rate": 7.96663382188616e-06,
+      "loss": 0.408,
+      "step": 109
+    },
+    {
+      "epoch": 0.3003412969283277,
+      "grad_norm": 0.16995355486869812,
+      "learning_rate": 7.93197766685348e-06,
+      "loss": 0.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.3030716723549488,
+      "grad_norm": 0.1682933270931244,
+      "learning_rate": 7.897105491022819e-06,
+      "loss": 0.4179,
+      "step": 111
+    },
+    {
+      "epoch": 0.30580204778156994,
+      "grad_norm": 0.15432436764240265,
+      "learning_rate": 7.862019863689075e-06,
+      "loss": 0.4037,
+      "step": 112
+    },
+    {
+      "epoch": 0.30853242320819113,
+      "grad_norm": 0.16314339637756348,
+      "learning_rate": 7.826723369873715e-06,
+      "loss": 0.4066,
+      "step": 113
+    },
+    {
+      "epoch": 0.31126279863481227,
+      "grad_norm": 0.17164085805416107,
+      "learning_rate": 7.791218610134324e-06,
+      "loss": 0.4328,
+      "step": 114
+    },
+    {
+      "epoch": 0.31399317406143346,
+      "grad_norm": 0.16329169273376465,
+      "learning_rate": 7.755508200373e-06,
+      "loss": 0.41,
+      "step": 115
+    },
+    {
+      "epoch": 0.3167235494880546,
+      "grad_norm": 0.15500546991825104,
+      "learning_rate": 7.719594771643623e-06,
+      "loss": 0.4023,
+      "step": 116
+    },
+    {
+      "epoch": 0.3194539249146758,
+      "grad_norm": 0.16174261271953583,
+      "learning_rate": 7.683480969958005e-06,
+      "loss": 0.4147,
+      "step": 117
+    },
+    {
+      "epoch": 0.3221843003412969,
+      "grad_norm": 0.16179116070270538,
+      "learning_rate": 7.647169456090925e-06,
+      "loss": 0.4198,
+      "step": 118
+    },
+    {
+      "epoch": 0.3249146757679181,
+      "grad_norm": 0.1634499430656433,
+      "learning_rate": 7.6106629053841255e-06,
+      "loss": 0.4162,
+      "step": 119
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.17482595145702362,
+      "learning_rate": 7.5739640075491546e-06,
+      "loss": 0.4304,
+      "step": 120
+    },
+    {
+      "epoch": 0.33037542662116043,
+      "grad_norm": 0.16381986439228058,
+      "learning_rate": 7.537075466469228e-06,
+      "loss": 0.4076,
+      "step": 121
+    },
+    {
+      "epoch": 0.33310580204778156,
+      "grad_norm": 0.15148329734802246,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3943,
+      "step": 122
+    },
+    {
+      "epoch": 0.33583617747440275,
+      "grad_norm": 0.17150920629501343,
+      "learning_rate": 7.462740339769323e-06,
+      "loss": 0.4221,
+      "step": 123
+    },
+    {
+      "epoch": 0.3385665529010239,
+      "grad_norm": 0.16451485455036163,
+      "learning_rate": 7.425299230975982e-06,
+      "loss": 0.3909,
+      "step": 124
+    },
+    {
+      "epoch": 0.3412969283276451,
+      "grad_norm": 0.1635640561580658,
+      "learning_rate": 7.387679432187442e-06,
+      "loss": 0.412,
+      "step": 125
+    },
+    {
+      "epoch": 0.3440273037542662,
+      "grad_norm": 0.15344786643981934,
+      "learning_rate": 7.349883715136601e-06,
+      "loss": 0.3957,
+      "step": 126
+    },
+    {
+      "epoch": 0.34675767918088735,
+      "grad_norm": 0.20929256081581116,
+      "learning_rate": 7.311914864517575e-06,
+      "loss": 0.4172,
+      "step": 127
+    },
+    {
+      "epoch": 0.34948805460750854,
+      "grad_norm": 0.15553469955921173,
+      "learning_rate": 7.27377567778053e-06,
+      "loss": 0.4255,
+      "step": 128
+    },
+    {
+      "epoch": 0.35221843003412967,
+      "grad_norm": 0.16687364876270294,
+      "learning_rate": 7.235468964925571e-06,
+      "loss": 0.4032,
+      "step": 129
+    },
+    {
+      "epoch": 0.35494880546075086,
+      "grad_norm": 0.15902447700500488,
+      "learning_rate": 7.1969975482957075e-06,
+      "loss": 0.4264,
+      "step": 130
+    },
+    {
+      "epoch": 0.357679180887372,
+      "grad_norm": 0.16279031336307526,
+      "learning_rate": 7.158364262368919e-06,
+      "loss": 0.4081,
+      "step": 131
+    },
+    {
+      "epoch": 0.3604095563139932,
+      "grad_norm": 0.1744302660226822,
+      "learning_rate": 7.119571953549305e-06,
+      "loss": 0.4439,
+      "step": 132
+    },
+    {
+      "epoch": 0.3631399317406143,
+      "grad_norm": 0.16045725345611572,
+      "learning_rate": 7.080623479957372e-06,
+      "loss": 0.3996,
+      "step": 133
+    },
+    {
+      "epoch": 0.3658703071672355,
+      "grad_norm": 0.16313788294792175,
+      "learning_rate": 7.041521711219468e-06,
+      "loss": 0.4055,
+      "step": 134
+    },
+    {
+      "epoch": 0.36860068259385664,
+      "grad_norm": 0.15558135509490967,
+      "learning_rate": 7.002269528256334e-06,
+      "loss": 0.4074,
+      "step": 135
+    },
+    {
+      "epoch": 0.37133105802047783,
+      "grad_norm": 0.16284853219985962,
+      "learning_rate": 6.9628698230708604e-06,
+      "loss": 0.3937,
+      "step": 136
+    },
+    {
+      "epoch": 0.37406143344709897,
+      "grad_norm": 0.1701689511537552,
+      "learning_rate": 6.9233254985350066e-06,
+      "loss": 0.4014,
+      "step": 137
+    },
+    {
+      "epoch": 0.37679180887372016,
+      "grad_norm": 0.16153037548065186,
+      "learning_rate": 6.883639468175926e-06,
+      "loss": 0.4345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3795221843003413,
+      "grad_norm": 0.15898269414901733,
+      "learning_rate": 6.843814655961302e-06,
+      "loss": 0.4117,
+      "step": 139
+    },
+    {
+      "epoch": 0.3822525597269625,
+      "grad_norm": 0.15082918107509613,
+      "learning_rate": 6.803853996083918e-06,
+      "loss": 0.4041,
+      "step": 140
+    },
+    {
+      "epoch": 0.3849829351535836,
+      "grad_norm": 0.15225613117218018,
+      "learning_rate": 6.763760432745475e-06,
+      "loss": 0.4203,
+      "step": 141
+    },
+    {
+      "epoch": 0.38771331058020475,
+      "grad_norm": 0.15860538184642792,
+      "learning_rate": 6.723536919939669e-06,
+      "loss": 0.409,
+      "step": 142
+    },
+    {
+      "epoch": 0.39044368600682594,
+      "grad_norm": 0.15701624751091003,
+      "learning_rate": 6.683186421234552e-06,
+      "loss": 0.411,
+      "step": 143
+    },
+    {
+      "epoch": 0.3931740614334471,
+      "grad_norm": 0.1592189222574234,
+      "learning_rate": 6.6427119095541745e-06,
+      "loss": 0.4034,
+      "step": 144
+    },
+    {
+      "epoch": 0.39590443686006827,
+      "grad_norm": 0.16646814346313477,
+      "learning_rate": 6.602116366959556e-06,
+      "loss": 0.411,
+      "step": 145
+    },
+    {
+      "epoch": 0.3986348122866894,
+      "grad_norm": 0.16729459166526794,
+      "learning_rate": 6.561402784428974e-06,
+      "loss": 0.4032,
+      "step": 146
+    },
+    {
+      "epoch": 0.4013651877133106,
+      "grad_norm": 0.16820791363716125,
+      "learning_rate": 6.520574161637591e-06,
+      "loss": 0.4087,
+      "step": 147
+    },
+    {
+      "epoch": 0.4040955631399317,
+      "grad_norm": 0.17279136180877686,
+      "learning_rate": 6.479633506736447e-06,
+      "loss": 0.3949,
+      "step": 148
+    },
+    {
+      "epoch": 0.4068259385665529,
+      "grad_norm": 0.15827003121376038,
+      "learning_rate": 6.438583836130835e-06,
+      "loss": 0.4134,
+      "step": 149
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.3199061155319214,
+      "learning_rate": 6.397428174258048e-06,
+      "loss": 0.3956,
+      "step": 150
+    },
+    {
+      "epoch": 0.41228668941979524,
+      "grad_norm": 0.15721672773361206,
+      "learning_rate": 6.3561695533645505e-06,
+      "loss": 0.408,
+      "step": 151
+    },
+    {
+      "epoch": 0.4150170648464164,
+      "grad_norm": 0.16460402309894562,
+      "learning_rate": 6.314811013282574e-06,
+      "loss": 0.4083,
+      "step": 152
+    },
+    {
+      "epoch": 0.41774744027303756,
+      "grad_norm": 0.156940758228302,
+      "learning_rate": 6.273355601206143e-06,
+      "loss": 0.4062,
+      "step": 153
+    },
+    {
+      "epoch": 0.4204778156996587,
+      "grad_norm": 0.15688540041446686,
+      "learning_rate": 6.231806371466574e-06,
+      "loss": 0.4051,
+      "step": 154
+    },
+    {
+      "epoch": 0.4232081911262799,
+      "grad_norm": 0.14866897463798523,
+      "learning_rate": 6.190166385307428e-06,
+      "loss": 0.4047,
+      "step": 155
+    },
+    {
+      "epoch": 0.425938566552901,
+      "grad_norm": 0.15852367877960205,
+      "learning_rate": 6.148438710658979e-06,
+      "loss": 0.4043,
+      "step": 156
+    },
+    {
+      "epoch": 0.4286689419795222,
+      "grad_norm": 0.1479935199022293,
+      "learning_rate": 6.106626421912163e-06,
+      "loss": 0.4073,
+      "step": 157
+    },
+    {
+      "epoch": 0.43139931740614335,
+      "grad_norm": 0.1690177172422409,
+      "learning_rate": 6.064732599692079e-06,
+      "loss": 0.4148,
+      "step": 158
+    },
+    {
+      "epoch": 0.4341296928327645,
+      "grad_norm": 0.1765451729297638,
+      "learning_rate": 6.022760330631006e-06,
+      "loss": 0.4105,
+      "step": 159
+    },
+    {
+      "epoch": 0.43686006825938567,
+      "grad_norm": 0.16014869511127472,
+      "learning_rate": 5.980712707140985e-06,
+      "loss": 0.4138,
+      "step": 160
+    },
+    {
+      "epoch": 0.4395904436860068,
+      "grad_norm": 0.1788393259048462,
+      "learning_rate": 5.938592827185994e-06,
+      "loss": 0.4224,
+      "step": 161
+    },
+    {
+      "epoch": 0.442320819112628,
+      "grad_norm": 0.1551506668329239,
+      "learning_rate": 5.896403794053679e-06,
+      "loss": 0.4058,
+      "step": 162
+    },
+    {
+      "epoch": 0.44505119453924913,
+      "grad_norm": 0.1573813110589981,
+      "learning_rate": 5.854148716126722e-06,
+      "loss": 0.4147,
+      "step": 163
+    },
+    {
+      "epoch": 0.4477815699658703,
+      "grad_norm": 0.16244283318519592,
+      "learning_rate": 5.811830706653819e-06,
+      "loss": 0.4152,
+      "step": 164
+    },
+    {
+      "epoch": 0.45051194539249145,
+      "grad_norm": 0.17180225253105164,
+      "learning_rate": 5.76945288352031e-06,
+      "loss": 0.3972,
+      "step": 165
+    },
+    {
+      "epoch": 0.45324232081911264,
+      "grad_norm": 0.16414454579353333,
+      "learning_rate": 5.72701836901845e-06,
+      "loss": 0.403,
+      "step": 166
+    },
+    {
+      "epoch": 0.4559726962457338,
+      "grad_norm": 0.3096899092197418,
+      "learning_rate": 5.684530289617377e-06,
+      "loss": 0.4195,
+      "step": 167
+    },
+    {
+      "epoch": 0.45870307167235497,
+      "grad_norm": 0.16957193613052368,
+      "learning_rate": 5.641991775732756e-06,
+      "loss": 0.405,
+      "step": 168
+    },
+    {
+      "epoch": 0.4614334470989761,
+      "grad_norm": 0.16117002069950104,
+      "learning_rate": 5.599405961496137e-06,
+      "loss": 0.398,
+      "step": 169
+    },
+    {
+      "epoch": 0.4641638225255973,
+      "grad_norm": 0.17450742423534393,
+      "learning_rate": 5.556775984524044e-06,
+      "loss": 0.4009,
+      "step": 170
+    },
+    {
+      "epoch": 0.4668941979522184,
+      "grad_norm": 0.15785841643810272,
+      "learning_rate": 5.514104985686802e-06,
+      "loss": 0.3838,
+      "step": 171
+    },
+    {
+      "epoch": 0.4696245733788396,
+      "grad_norm": 0.22598251700401306,
+      "learning_rate": 5.471396108877123e-06,
+      "loss": 0.4176,
+      "step": 172
+    },
+    {
+      "epoch": 0.47235494880546075,
+      "grad_norm": 0.17126567661762238,
+      "learning_rate": 5.428652500778472e-06,
+      "loss": 0.4135,
+      "step": 173
+    },
+    {
+      "epoch": 0.4750853242320819,
+      "grad_norm": 0.1700679510831833,
+      "learning_rate": 5.385877310633233e-06,
+      "loss": 0.4259,
+      "step": 174
+    },
+    {
+      "epoch": 0.4778156996587031,
+      "grad_norm": 0.1624089628458023,
+      "learning_rate": 5.3430736900106715e-06,
+      "loss": 0.4425,
+      "step": 175
+    },
+    {
+      "epoch": 0.4805460750853242,
+      "grad_norm": 0.15028750896453857,
+      "learning_rate": 5.300244792574743e-06,
+      "loss": 0.3966,
+      "step": 176
+    },
+    {
+      "epoch": 0.4832764505119454,
+      "grad_norm": 0.17664162814617157,
+      "learning_rate": 5.257393773851733e-06,
+      "loss": 0.4125,
+      "step": 177
+    },
+    {
+      "epoch": 0.48600682593856653,
+      "grad_norm": 0.16111449897289276,
+      "learning_rate": 5.214523790997773e-06,
+      "loss": 0.4046,
+      "step": 178
+    },
+    {
+      "epoch": 0.4887372013651877,
+      "grad_norm": 0.17330825328826904,
+      "learning_rate": 5.171638002566218e-06,
+      "loss": 0.4054,
+      "step": 179
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.1512707620859146,
+      "learning_rate": 5.1287395682749444e-06,
+      "loss": 0.4014,
+      "step": 180
+    },
+    {
+      "epoch": 0.49419795221843005,
+      "grad_norm": 0.15316011011600494,
+      "learning_rate": 5.0858316487735385e-06,
+      "loss": 0.4013,
+      "step": 181
+    },
+    {
+      "epoch": 0.4969283276450512,
+      "grad_norm": 0.14988335967063904,
+      "learning_rate": 5.042917405410436e-06,
+      "loss": 0.3953,
+      "step": 182
+    },
+    {
+      "epoch": 0.49965870307167237,
+      "grad_norm": 0.17286710441112518,
+      "learning_rate": 5e-06,
+      "loss": 0.407,
+      "step": 183
+    },
+    {
+      "epoch": 0.5023890784982935,
+      "grad_norm": 0.16462546586990356,
+      "learning_rate": 4.957082594589566e-06,
+      "loss": 0.4017,
+      "step": 184
+    },
+    {
+      "epoch": 0.5051194539249146,
+      "grad_norm": 0.15909536182880402,
+      "learning_rate": 4.914168351226463e-06,
+      "loss": 0.3977,
+      "step": 185
+    },
+    {
+      "epoch": 0.5078498293515359,
+      "grad_norm": 0.1730009764432907,
+      "learning_rate": 4.871260431725058e-06,
+      "loss": 0.4271,
+      "step": 186
+    },
+    {
+      "epoch": 0.510580204778157,
+      "grad_norm": 0.17171163856983185,
+      "learning_rate": 4.828361997433783e-06,
+      "loss": 0.4169,
+      "step": 187
+    },
+    {
+      "epoch": 0.5133105802047782,
+      "grad_norm": 0.14412260055541992,
+      "learning_rate": 4.7854762090022274e-06,
+      "loss": 0.3782,
+      "step": 188
+    },
+    {
+      "epoch": 0.5160409556313993,
+      "grad_norm": 0.1570647805929184,
+      "learning_rate": 4.742606226148268e-06,
+      "loss": 0.4034,
+      "step": 189
+    },
+    {
+      "epoch": 0.5187713310580204,
+      "grad_norm": 0.14350539445877075,
+      "learning_rate": 4.699755207425259e-06,
+      "loss": 0.403,
+      "step": 190
+    },
+    {
+      "epoch": 0.5215017064846417,
+      "grad_norm": 0.17106682062149048,
+      "learning_rate": 4.65692630998933e-06,
+      "loss": 0.4087,
+      "step": 191
+    },
+    {
+      "epoch": 0.5242320819112628,
+      "grad_norm": 0.18561221659183502,
+      "learning_rate": 4.614122689366769e-06,
+      "loss": 0.4093,
+      "step": 192
+    },
+    {
+      "epoch": 0.5269624573378839,
+      "grad_norm": 0.15318401157855988,
+      "learning_rate": 4.571347499221528e-06,
+      "loss": 0.4,
+      "step": 193
+    },
+    {
+      "epoch": 0.5296928327645051,
+      "grad_norm": 0.150321364402771,
+      "learning_rate": 4.528603891122878e-06,
+      "loss": 0.4028,
+      "step": 194
+    },
+    {
+      "epoch": 0.5324232081911263,
+      "grad_norm": 0.15496495366096497,
+      "learning_rate": 4.485895014313198e-06,
+      "loss": 0.418,
+      "step": 195
+    },
+    {
+      "epoch": 0.5351535836177475,
+      "grad_norm": 0.1591518372297287,
+      "learning_rate": 4.443224015475956e-06,
+      "loss": 0.4122,
+      "step": 196
+    },
+    {
+      "epoch": 0.5378839590443686,
+      "grad_norm": 0.16226577758789062,
+      "learning_rate": 4.400594038503864e-06,
+      "loss": 0.4249,
+      "step": 197
+    },
+    {
+      "epoch": 0.5406143344709897,
+      "grad_norm": 0.21725980937480927,
+      "learning_rate": 4.358008224267245e-06,
+      "loss": 0.4005,
+      "step": 198
+    },
+    {
+      "epoch": 0.543344709897611,
+      "grad_norm": 0.16464541852474213,
+      "learning_rate": 4.3154697103826235e-06,
+      "loss": 0.4058,
+      "step": 199
+    },
+    {
+      "epoch": 0.5460750853242321,
+      "grad_norm": 0.15310809016227722,
+      "learning_rate": 4.272981630981551e-06,
+      "loss": 0.4049,
+      "step": 200
+    },
+    {
+      "epoch": 0.5488054607508532,
+      "grad_norm": 0.16250354051589966,
+      "learning_rate": 4.230547116479691e-06,
+      "loss": 0.3779,
+      "step": 201
+    },
+    {
+      "epoch": 0.5515358361774744,
+      "grad_norm": 0.14419779181480408,
+      "learning_rate": 4.1881692933461835e-06,
+      "loss": 0.4129,
+      "step": 202
+    },
+    {
+      "epoch": 0.5542662116040956,
+      "grad_norm": 0.1601477712392807,
+      "learning_rate": 4.14585128387328e-06,
+      "loss": 0.3993,
+      "step": 203
+    },
+    {
+      "epoch": 0.5569965870307167,
+      "grad_norm": 0.16939853131771088,
+      "learning_rate": 4.103596205946323e-06,
+      "loss": 0.3928,
+      "step": 204
+    },
+    {
+      "epoch": 0.5597269624573379,
+      "grad_norm": 0.14936766028404236,
+      "learning_rate": 4.061407172814008e-06,
+      "loss": 0.4118,
+      "step": 205
+    },
+    {
+      "epoch": 0.562457337883959,
+      "grad_norm": 0.1553383320569992,
+      "learning_rate": 4.019287292859016e-06,
+      "loss": 0.4031,
+      "step": 206
+    },
+    {
+      "epoch": 0.5651877133105802,
+      "grad_norm": 0.1629059761762619,
+      "learning_rate": 3.977239669368998e-06,
+      "loss": 0.4143,
+      "step": 207
+    },
+    {
+      "epoch": 0.5679180887372014,
+      "grad_norm": 0.147048220038414,
+      "learning_rate": 3.9352674003079225e-06,
+      "loss": 0.3907,
+      "step": 208
+    },
+    {
+      "epoch": 0.5706484641638225,
+      "grad_norm": 0.1578659862279892,
+      "learning_rate": 3.893373578087838e-06,
+      "loss": 0.4011,
+      "step": 209
+    },
+    {
+      "epoch": 0.5733788395904437,
+      "grad_norm": 0.15005314350128174,
+      "learning_rate": 3.851561289341023e-06,
+      "loss": 0.4038,
+      "step": 210
+    },
+    {
+      "epoch": 0.5761092150170648,
+      "grad_norm": 0.16171501576900482,
+      "learning_rate": 3.8098336146925728e-06,
+      "loss": 0.395,
+      "step": 211
+    },
+    {
+      "epoch": 0.578839590443686,
+      "grad_norm": 0.17219065129756927,
+      "learning_rate": 3.768193628533427e-06,
+      "loss": 0.4064,
+      "step": 212
+    },
+    {
+      "epoch": 0.5815699658703072,
+      "grad_norm": 0.14859041571617126,
+      "learning_rate": 3.726644398793857e-06,
+      "loss": 0.4054,
+      "step": 213
+    },
+    {
+      "epoch": 0.5843003412969283,
+      "grad_norm": 0.16669155657291412,
+      "learning_rate": 3.685188986717427e-06,
+      "loss": 0.4145,
+      "step": 214
+    },
+    {
+      "epoch": 0.5870307167235495,
+      "grad_norm": 0.16787604987621307,
+      "learning_rate": 3.6438304466354503e-06,
+      "loss": 0.4329,
+      "step": 215
+    },
+    {
+      "epoch": 0.5897610921501707,
+      "grad_norm": 0.17759054899215698,
+      "learning_rate": 3.6025718257419532e-06,
+      "loss": 0.4238,
+      "step": 216
+    },
+    {
+      "epoch": 0.5924914675767918,
+      "grad_norm": 0.15464290976524353,
+      "learning_rate": 3.5614161638691657e-06,
+      "loss": 0.4122,
+      "step": 217
+    },
+    {
+      "epoch": 0.595221843003413,
+      "grad_norm": 0.146434485912323,
+      "learning_rate": 3.520366493263554e-06,
+      "loss": 0.4004,
+      "step": 218
+    },
+    {
+      "epoch": 0.5979522184300341,
+      "grad_norm": 0.15158678591251373,
+      "learning_rate": 3.4794258383624115e-06,
+      "loss": 0.4246,
+      "step": 219
+    },
+    {
+      "epoch": 0.6006825938566553,
+      "grad_norm": 0.17705509066581726,
+      "learning_rate": 3.4385972155710274e-06,
+      "loss": 0.4105,
+      "step": 220
+    },
+    {
+      "epoch": 0.6034129692832765,
+      "grad_norm": 0.15027230978012085,
+      "learning_rate": 3.3978836330404453e-06,
+      "loss": 0.4264,
+      "step": 221
+    },
+    {
+      "epoch": 0.6061433447098976,
+      "grad_norm": 0.14981985092163086,
+      "learning_rate": 3.3572880904458267e-06,
+      "loss": 0.4188,
+      "step": 222
+    },
+    {
+      "epoch": 0.6088737201365187,
+      "grad_norm": 0.15152880549430847,
+      "learning_rate": 3.3168135787654493e-06,
+      "loss": 0.3935,
+      "step": 223
+    },
+    {
+      "epoch": 0.6116040955631399,
+      "grad_norm": 0.15876388549804688,
+      "learning_rate": 3.2764630800603314e-06,
+      "loss": 0.4193,
+      "step": 224
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 0.15047837793827057,
+      "learning_rate": 3.236239567254526e-06,
+      "loss": 0.3916,
+      "step": 225
+    },
+    {
+      "epoch": 0.6170648464163823,
+      "grad_norm": 0.15240547060966492,
+      "learning_rate": 3.1961460039160842e-06,
+      "loss": 0.4187,
+      "step": 226
+    },
+    {
+      "epoch": 0.6197952218430034,
+      "grad_norm": 0.15835705399513245,
+      "learning_rate": 3.1561853440387e-06,
+      "loss": 0.4008,
+      "step": 227
+    },
+    {
+      "epoch": 0.6225255972696245,
+      "grad_norm": 0.16235880553722382,
+      "learning_rate": 3.116360531824074e-06,
+      "loss": 0.4239,
+      "step": 228
+    },
+    {
+      "epoch": 0.6252559726962458,
+      "grad_norm": 0.16306978464126587,
+      "learning_rate": 3.076674501464994e-06,
+      "loss": 0.4139,
+      "step": 229
+    },
+    {
+      "epoch": 0.6279863481228669,
+      "grad_norm": 0.14479714632034302,
+      "learning_rate": 3.0371301769291417e-06,
+      "loss": 0.4157,
+      "step": 230
+    },
+    {
+      "epoch": 0.630716723549488,
+      "grad_norm": 0.1663469821214676,
+      "learning_rate": 2.997730471743667e-06,
+      "loss": 0.4301,
+      "step": 231
+    },
+    {
+      "epoch": 0.6334470989761092,
+      "grad_norm": 0.1759214997291565,
+      "learning_rate": 2.958478288780533e-06,
+      "loss": 0.3993,
+      "step": 232
+    },
+    {
+      "epoch": 0.6361774744027304,
+      "grad_norm": 0.1472492516040802,
+      "learning_rate": 2.919376520042628e-06,
+      "loss": 0.3998,
+      "step": 233
+    },
+    {
+      "epoch": 0.6389078498293516,
+      "grad_norm": 0.14618809521198273,
+      "learning_rate": 2.880428046450697e-06,
+      "loss": 0.3921,
+      "step": 234
+    },
+    {
+      "epoch": 0.6416382252559727,
+      "grad_norm": 0.1660156548023224,
+      "learning_rate": 2.8416357376310823e-06,
+      "loss": 0.4095,
+      "step": 235
+    },
+    {
+      "epoch": 0.6443686006825938,
+      "grad_norm": 0.1544540971517563,
+      "learning_rate": 2.8030024517042907e-06,
+      "loss": 0.4112,
+      "step": 236
+    },
+    {
+      "epoch": 0.647098976109215,
+      "grad_norm": 0.1531461477279663,
+      "learning_rate": 2.7645310350744296e-06,
+      "loss": 0.4079,
+      "step": 237
+    },
+    {
+      "epoch": 0.6498293515358362,
+      "grad_norm": 0.16143448650836945,
+      "learning_rate": 2.7262243222194728e-06,
+      "loss": 0.4088,
+      "step": 238
+    },
+    {
+      "epoch": 0.6525597269624573,
+      "grad_norm": 0.1632911115884781,
+      "learning_rate": 2.6880851354824277e-06,
+      "loss": 0.406,
+      "step": 239
+    },
+    {
+      "epoch": 0.6552901023890785,
+      "grad_norm": 0.15283940732479095,
+      "learning_rate": 2.6501162848634023e-06,
+      "loss": 0.3922,
+      "step": 240
+    },
+    {
+      "epoch": 0.6580204778156996,
+      "grad_norm": 0.15318641066551208,
+      "learning_rate": 2.6123205678125597e-06,
+      "loss": 0.39,
+      "step": 241
+    },
+    {
+      "epoch": 0.6607508532423209,
+      "grad_norm": 0.15297549962997437,
+      "learning_rate": 2.57470076902402e-06,
+      "loss": 0.3991,
+      "step": 242
+    },
+    {
+      "epoch": 0.663481228668942,
+      "grad_norm": 0.1510440558195114,
+      "learning_rate": 2.537259660230679e-06,
+      "loss": 0.418,
+      "step": 243
+    },
+    {
+      "epoch": 0.6662116040955631,
+      "grad_norm": 0.14892160892486572,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.3863,
+      "step": 244
+    },
+    {
+      "epoch": 0.6689419795221843,
+      "grad_norm": 0.1641772985458374,
+      "learning_rate": 2.462924533530774e-06,
+      "loss": 0.4333,
+      "step": 245
+    },
+    {
+      "epoch": 0.6716723549488055,
+      "grad_norm": 0.15933027863502502,
+      "learning_rate": 2.426035992450848e-06,
+      "loss": 0.4064,
+      "step": 246
+    },
+    {
+      "epoch": 0.6744027303754266,
+      "grad_norm": 0.14534929394721985,
+      "learning_rate": 2.3893370946158758e-06,
+      "loss": 0.404,
+      "step": 247
+    },
+    {
+      "epoch": 0.6771331058020478,
+      "grad_norm": 0.1527319997549057,
+      "learning_rate": 2.3528305439090744e-06,
+      "loss": 0.4081,
+      "step": 248
+    },
+    {
+      "epoch": 0.6798634812286689,
+      "grad_norm": 0.15615414083003998,
+      "learning_rate": 2.316519030041998e-06,
+      "loss": 0.4067,
+      "step": 249
+    },
+    {
+      "epoch": 0.6825938566552902,
+      "grad_norm": 0.17054639756679535,
+      "learning_rate": 2.280405228356377e-06,
+      "loss": 0.4088,
+      "step": 250
+    },
+    {
+      "epoch": 0.6853242320819113,
+      "grad_norm": 0.163183331489563,
+      "learning_rate": 2.2444917996270003e-06,
+      "loss": 0.4131,
+      "step": 251
+    },
+    {
+      "epoch": 0.6880546075085324,
+      "grad_norm": 0.15478871762752533,
+      "learning_rate": 2.2087813898656775e-06,
+      "loss": 0.4161,
+      "step": 252
+    },
+    {
+      "epoch": 0.6907849829351536,
+      "grad_norm": 0.15877461433410645,
+      "learning_rate": 2.173276630126287e-06,
+      "loss": 0.3991,
+      "step": 253
+    },
+    {
+      "epoch": 0.6935153583617747,
+      "grad_norm": 0.16762347519397736,
+      "learning_rate": 2.137980136310926e-06,
+      "loss": 0.4094,
+      "step": 254
+    },
+    {
+      "epoch": 0.6962457337883959,
+      "grad_norm": 0.1578551083803177,
+      "learning_rate": 2.102894508977182e-06,
+      "loss": 0.4108,
+      "step": 255
+    },
+    {
+      "epoch": 0.6989761092150171,
+      "grad_norm": 0.17313554883003235,
+      "learning_rate": 2.0680223331465223e-06,
+      "loss": 0.4112,
+      "step": 256
+    },
+    {
+      "epoch": 0.7017064846416382,
+      "grad_norm": 0.1474330574274063,
+      "learning_rate": 2.033366178113841e-06,
+      "loss": 0.3995,
+      "step": 257
+    },
+    {
+      "epoch": 0.7044368600682593,
+      "grad_norm": 0.15970253944396973,
+      "learning_rate": 1.9989285972581595e-06,
+      "loss": 0.3998,
+      "step": 258
+    },
+    {
+      "epoch": 0.7071672354948806,
+      "grad_norm": 0.1546693742275238,
+      "learning_rate": 1.9647121278544996e-06,
+      "loss": 0.3908,
+      "step": 259
+    },
+    {
+      "epoch": 0.7098976109215017,
+      "grad_norm": 0.15894074738025665,
+      "learning_rate": 1.93071929088694e-06,
+      "loss": 0.4179,
+      "step": 260
+    },
+    {
+      "epoch": 0.7126279863481229,
+      "grad_norm": 0.15951929986476898,
+      "learning_rate": 1.896952590862886e-06,
+      "loss": 0.407,
+      "step": 261
+    },
+    {
+      "epoch": 0.715358361774744,
+      "grad_norm": 0.145669087767601,
+      "learning_rate": 1.8634145156285311e-06,
+      "loss": 0.3863,
+      "step": 262
+    },
+    {
+      "epoch": 0.7180887372013652,
+      "grad_norm": 0.16664068400859833,
+      "learning_rate": 1.8301075361855674e-06,
+      "loss": 0.3965,
+      "step": 263
+    },
+    {
+      "epoch": 0.7208191126279864,
+      "grad_norm": 0.15179961919784546,
+      "learning_rate": 1.7970341065091246e-06,
+      "loss": 0.3872,
+      "step": 264
+    },
+    {
+      "epoch": 0.7235494880546075,
+      "grad_norm": 0.16116613149642944,
+      "learning_rate": 1.7641966633669705e-06,
+      "loss": 0.4082,
+      "step": 265
+    },
+    {
+      "epoch": 0.7262798634812286,
+      "grad_norm": 0.15431508421897888,
+      "learning_rate": 1.7315976261399698e-06,
+      "loss": 0.4136,
+      "step": 266
+    },
+    {
+      "epoch": 0.7290102389078499,
+      "grad_norm": 0.1545833945274353,
+      "learning_rate": 1.699239396643841e-06,
+      "loss": 0.3969,
+      "step": 267
+    },
+    {
+      "epoch": 0.731740614334471,
+      "grad_norm": 0.1713000386953354,
+      "learning_rate": 1.667124358952184e-06,
+      "loss": 0.4188,
+      "step": 268
+    },
+    {
+      "epoch": 0.7344709897610922,
+      "grad_norm": 0.16345979273319244,
+      "learning_rate": 1.6352548792208356e-06,
+      "loss": 0.4029,
+      "step": 269
+    },
+    {
+      "epoch": 0.7372013651877133,
+      "grad_norm": 0.14592435956001282,
+      "learning_rate": 1.6036333055135345e-06,
+      "loss": 0.4044,
+      "step": 270
+    },
+    {
+      "epoch": 0.7399317406143344,
+      "grad_norm": 0.1973186582326889,
+      "learning_rate": 1.572261967628923e-06,
+      "loss": 0.3998,
+      "step": 271
+    },
+    {
+      "epoch": 0.7426621160409557,
+      "grad_norm": 0.15132401883602142,
+      "learning_rate": 1.541143176928891e-06,
+      "loss": 0.3928,
+      "step": 272
+    },
+    {
+      "epoch": 0.7453924914675768,
+      "grad_norm": 0.1545684039592743,
+      "learning_rate": 1.5102792261682813e-06,
+      "loss": 0.3963,
+      "step": 273
+    },
+    {
+      "epoch": 0.7481228668941979,
+      "grad_norm": 0.1502438336610794,
+      "learning_rate": 1.4796723893259712e-06,
+      "loss": 0.4006,
+      "step": 274
+    },
+    {
+      "epoch": 0.7508532423208191,
+      "grad_norm": 0.15633085370063782,
+      "learning_rate": 1.4493249214373224e-06,
+      "loss": 0.3979,
+      "step": 275
+    },
+    {
+      "epoch": 0.7535836177474403,
+      "grad_norm": 0.15326417982578278,
+      "learning_rate": 1.4192390584280347e-06,
+      "loss": 0.4017,
+      "step": 276
+    },
+    {
+      "epoch": 0.7563139931740614,
+      "grad_norm": 0.1504485011100769,
+      "learning_rate": 1.3894170169494192e-06,
+      "loss": 0.4146,
+      "step": 277
+    },
+    {
+      "epoch": 0.7590443686006826,
+      "grad_norm": 0.1470741629600525,
+      "learning_rate": 1.3598609942150765e-06,
+      "loss": 0.3954,
+      "step": 278
+    },
+    {
+      "epoch": 0.7617747440273037,
+      "grad_norm": 0.16345715522766113,
+      "learning_rate": 1.330573167839005e-06,
+      "loss": 0.409,
+      "step": 279
+    },
+    {
+      "epoch": 0.764505119453925,
+      "grad_norm": 0.15342997014522552,
+      "learning_rate": 1.3015556956751669e-06,
+      "loss": 0.4002,
+      "step": 280
+    },
+    {
+      "epoch": 0.7672354948805461,
+      "grad_norm": 0.1575509011745453,
+      "learning_rate": 1.2728107156585e-06,
+      "loss": 0.4176,
+      "step": 281
+    },
+    {
+      "epoch": 0.7699658703071672,
+      "grad_norm": 0.1618194580078125,
+      "learning_rate": 1.2443403456474017e-06,
+      "loss": 0.3958,
+      "step": 282
+    },
+    {
+      "epoch": 0.7726962457337884,
+      "grad_norm": 0.15315888822078705,
+      "learning_rate": 1.2161466832676888e-06,
+      "loss": 0.4045,
+      "step": 283
+    },
+    {
+      "epoch": 0.7754266211604095,
+      "grad_norm": 0.14545629918575287,
+      "learning_rate": 1.188231805758049e-06,
+      "loss": 0.3981,
+      "step": 284
+    },
+    {
+      "epoch": 0.7781569965870307,
+      "grad_norm": 0.17285780608654022,
+      "learning_rate": 1.1605977698170001e-06,
+      "loss": 0.416,
+      "step": 285
+    },
+    {
+      "epoch": 0.7808873720136519,
+      "grad_norm": 0.15523703396320343,
+      "learning_rate": 1.1332466114513512e-06,
+      "loss": 0.4163,
+      "step": 286
+    },
+    {
+      "epoch": 0.783617747440273,
+      "grad_norm": 0.15426713228225708,
+      "learning_rate": 1.1061803458261977e-06,
+      "loss": 0.405,
+      "step": 287
+    },
+    {
+      "epoch": 0.7863481228668942,
+      "grad_norm": 0.15107548236846924,
+      "learning_rate": 1.0794009671164484e-06,
+      "loss": 0.3818,
+      "step": 288
+    },
+    {
+      "epoch": 0.7890784982935154,
+      "grad_norm": 0.15870976448059082,
+      "learning_rate": 1.0529104483599023e-06,
+      "loss": 0.4044,
+      "step": 289
+    },
+    {
+      "epoch": 0.7918088737201365,
+      "grad_norm": 0.16166147589683533,
+      "learning_rate": 1.0267107413118743e-06,
+      "loss": 0.4029,
+      "step": 290
+    },
+    {
+      "epoch": 0.7945392491467577,
+      "grad_norm": 0.15707789361476898,
+      "learning_rate": 1.0008037763014033e-06,
+      "loss": 0.3903,
+      "step": 291
+    },
+    {
+      "epoch": 0.7972696245733788,
+      "grad_norm": 0.17786303162574768,
+      "learning_rate": 9.751914620890208e-07,
+      "loss": 0.4083,
+      "step": 292
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.153977632522583,
+      "learning_rate": 9.498756857261243e-07,
+      "loss": 0.4119,
+      "step": 293
+    },
+    {
+      "epoch": 0.8027303754266212,
+      "grad_norm": 0.15868696570396423,
+      "learning_rate": 9.248583124159438e-07,
+      "loss": 0.4064,
+      "step": 294
+    },
+    {
+      "epoch": 0.8054607508532423,
+      "grad_norm": 0.16338956356048584,
+      "learning_rate": 9.00141185376115e-07,
+      "loss": 0.4042,
+      "step": 295
+    },
+    {
+      "epoch": 0.8081911262798634,
+      "grad_norm": 0.14950022101402283,
+      "learning_rate": 8.757261257028776e-07,
+      "loss": 0.396,
+      "step": 296
+    },
+    {
+      "epoch": 0.8109215017064847,
+      "grad_norm": 0.15251553058624268,
+      "learning_rate": 8.516149322369055e-07,
+      "loss": 0.4055,
+      "step": 297
+    },
+    {
+      "epoch": 0.8136518771331058,
+      "grad_norm": 0.16309964656829834,
+      "learning_rate": 8.278093814307637e-07,
+      "loss": 0.3992,
+      "step": 298
+    },
+    {
+      "epoch": 0.816382252559727,
+      "grad_norm": 0.1547779142856598,
+      "learning_rate": 8.043112272180309e-07,
+      "loss": 0.3959,
+      "step": 299
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.16333834826946259,
+      "learning_rate": 7.811222008840719e-07,
+      "loss": 0.401,
+      "step": 300
+    },
+    {
+      "epoch": 0.8218430034129692,
+      "grad_norm": 0.15523184835910797,
+      "learning_rate": 7.582440109384808e-07,
+      "loss": 0.4155,
+      "step": 301
+    },
+    {
+      "epoch": 0.8245733788395905,
+      "grad_norm": 0.16227498650550842,
+      "learning_rate": 7.356783429892022e-07,
+      "loss": 0.4136,
+      "step": 302
+    },
+    {
+      "epoch": 0.8273037542662116,
+      "grad_norm": 0.15816375613212585,
+      "learning_rate": 7.13426859618338e-07,
+      "loss": 0.3908,
+      "step": 303
+    },
+    {
+      "epoch": 0.8300341296928327,
+      "grad_norm": 0.15553700923919678,
+      "learning_rate": 6.914912002596591e-07,
+      "loss": 0.4067,
+      "step": 304
+    },
+    {
+      "epoch": 0.8327645051194539,
+      "grad_norm": 0.15649977326393127,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.4201,
+      "step": 305
+    },
+    {
+      "epoch": 0.8354948805460751,
+      "grad_norm": 0.15133178234100342,
+      "learning_rate": 6.485737948492237e-07,
+      "loss": 0.4078,
+      "step": 306
+    },
+    {
+      "epoch": 0.8382252559726963,
+      "grad_norm": 0.15972872078418732,
+      "learning_rate": 6.275952108448019e-07,
+      "loss": 0.4258,
+      "step": 307
+    },
+    {
+      "epoch": 0.8409556313993174,
+      "grad_norm": 0.15277239680290222,
+      "learning_rate": 6.069387747142591e-07,
+      "loss": 0.4098,
+      "step": 308
+    },
+    {
+      "epoch": 0.8436860068259385,
+      "grad_norm": 0.14945055544376373,
+      "learning_rate": 5.866060083722624e-07,
+      "loss": 0.3911,
+      "step": 309
+    },
+    {
+      "epoch": 0.8464163822525598,
+      "grad_norm": 0.1511884182691574,
+      "learning_rate": 5.665984098862992e-07,
+      "loss": 0.4025,
+      "step": 310
+    },
+    {
+      "epoch": 0.8491467576791809,
+      "grad_norm": 0.15586020052433014,
+      "learning_rate": 5.46917453366298e-07,
+      "loss": 0.4145,
+      "step": 311
+    },
+    {
+      "epoch": 0.851877133105802,
+      "grad_norm": 0.14383640885353088,
+      "learning_rate": 5.275645888560233e-07,
+      "loss": 0.3878,
+      "step": 312
+    },
+    {
+      "epoch": 0.8546075085324232,
+      "grad_norm": 0.1596316248178482,
+      "learning_rate": 5.085412422262364e-07,
+      "loss": 0.4217,
+      "step": 313
+    },
+    {
+      "epoch": 0.8573378839590444,
+      "grad_norm": 0.20000702142715454,
+      "learning_rate": 4.898488150696468e-07,
+      "loss": 0.407,
+      "step": 314
+    },
+    {
+      "epoch": 0.8600682593856656,
+      "grad_norm": 0.14647561311721802,
+      "learning_rate": 4.71488684597643e-07,
+      "loss": 0.3892,
+      "step": 315
+    },
+    {
+      "epoch": 0.8627986348122867,
+      "grad_norm": 0.16477878391742706,
+      "learning_rate": 4.534622035388214e-07,
+      "loss": 0.4089,
+      "step": 316
+    },
+    {
+      "epoch": 0.8655290102389078,
+      "grad_norm": 0.1526196449995041,
+      "learning_rate": 4.3577070003932243e-07,
+      "loss": 0.4051,
+      "step": 317
+    },
+    {
+      "epoch": 0.868259385665529,
+      "grad_norm": 0.1495794653892517,
+      "learning_rate": 4.184154775649768e-07,
+      "loss": 0.3971,
+      "step": 318
+    },
+    {
+      "epoch": 0.8709897610921502,
+      "grad_norm": 0.15723681449890137,
+      "learning_rate": 4.0139781480526776e-07,
+      "loss": 0.4072,
+      "step": 319
+    },
+    {
+      "epoch": 0.8737201365187713,
+      "grad_norm": 0.15380658209323883,
+      "learning_rate": 3.8471896557912005e-07,
+      "loss": 0.3872,
+      "step": 320
+    },
+    {
+      "epoch": 0.8764505119453925,
+      "grad_norm": 0.1472550332546234,
+      "learning_rate": 3.683801587425251e-07,
+      "loss": 0.3908,
+      "step": 321
+    },
+    {
+      "epoch": 0.8791808873720136,
+      "grad_norm": 0.15712445974349976,
+      "learning_rate": 3.523825980979989e-07,
+      "loss": 0.4249,
+      "step": 322
+    },
+    {
+      "epoch": 0.8819112627986349,
+      "grad_norm": 0.15364351868629456,
+      "learning_rate": 3.3672746230588803e-07,
+      "loss": 0.4111,
+      "step": 323
+    },
+    {
+      "epoch": 0.884641638225256,
+      "grad_norm": 0.15788617730140686,
+      "learning_rate": 3.214159047975324e-07,
+      "loss": 0.4082,
+      "step": 324
+    },
+    {
+      "epoch": 0.8873720136518771,
+      "grad_norm": 0.14652356505393982,
+      "learning_rate": 3.0644905369027923e-07,
+      "loss": 0.3982,
+      "step": 325
+    },
+    {
+      "epoch": 0.8901023890784983,
+      "grad_norm": 0.14735613763332367,
+      "learning_rate": 2.918280117043709e-07,
+      "loss": 0.3879,
+      "step": 326
+    },
+    {
+      "epoch": 0.8928327645051195,
+      "grad_norm": 0.16827955842018127,
+      "learning_rate": 2.7755385608169374e-07,
+      "loss": 0.3995,
+      "step": 327
+    },
+    {
+      "epoch": 0.8955631399317406,
+      "grad_norm": 0.14965175092220306,
+      "learning_rate": 2.636276385064157e-07,
+      "loss": 0.4042,
+      "step": 328
+    },
+    {
+      "epoch": 0.8982935153583618,
+      "grad_norm": 0.15481331944465637,
+      "learning_rate": 2.500503850274949e-07,
+      "loss": 0.4204,
+      "step": 329
+    },
+    {
+      "epoch": 0.9010238907849829,
+      "grad_norm": 0.15071091055870056,
+      "learning_rate": 2.368230959830875e-07,
+      "loss": 0.399,
+      "step": 330
+    },
+    {
+      "epoch": 0.903754266211604,
+      "grad_norm": 0.1542576551437378,
+      "learning_rate": 2.2394674592684184e-07,
+      "loss": 0.4111,
+      "step": 331
+    },
+    {
+      "epoch": 0.9064846416382253,
+      "grad_norm": 0.16701681911945343,
+      "learning_rate": 2.1142228355609862e-07,
+      "loss": 0.4021,
+      "step": 332
+    },
+    {
+      "epoch": 0.9092150170648464,
+      "grad_norm": 0.15246938169002533,
+      "learning_rate": 1.992506316419912e-07,
+      "loss": 0.3869,
+      "step": 333
+    },
+    {
+      "epoch": 0.9119453924914676,
+      "grad_norm": 0.16509276628494263,
+      "learning_rate": 1.8743268696145956e-07,
+      "loss": 0.404,
+      "step": 334
+    },
+    {
+      "epoch": 0.9146757679180887,
+      "grad_norm": 0.18542227149009705,
+      "learning_rate": 1.7596932023117687e-07,
+      "loss": 0.4085,
+      "step": 335
+    },
+    {
+      "epoch": 0.9174061433447099,
+      "grad_norm": 0.1459270566701889,
+      "learning_rate": 1.6486137604339813e-07,
+      "loss": 0.3927,
+      "step": 336
+    },
+    {
+      "epoch": 0.9201365187713311,
+      "grad_norm": 0.1526777148246765,
+      "learning_rate": 1.5410967280373222e-07,
+      "loss": 0.4126,
+      "step": 337
+    },
+    {
+      "epoch": 0.9228668941979522,
+      "grad_norm": 0.1446801722049713,
+      "learning_rate": 1.4371500267084337e-07,
+      "loss": 0.3948,
+      "step": 338
+    },
+    {
+      "epoch": 0.9255972696245733,
+      "grad_norm": 0.15509983897209167,
+      "learning_rate": 1.3367813149808728e-07,
+      "loss": 0.4012,
+      "step": 339
+    },
+    {
+      "epoch": 0.9283276450511946,
+      "grad_norm": 0.16408248245716095,
+      "learning_rate": 1.2399979877708746e-07,
+      "loss": 0.3972,
+      "step": 340
+    },
+    {
+      "epoch": 0.9310580204778157,
+      "grad_norm": 0.1493483930826187,
+      "learning_rate": 1.1468071758324595e-07,
+      "loss": 0.4017,
+      "step": 341
+    },
+    {
+      "epoch": 0.9337883959044369,
+      "grad_norm": 0.14702877402305603,
+      "learning_rate": 1.0572157452321097e-07,
+      "loss": 0.3958,
+      "step": 342
+    },
+    {
+      "epoch": 0.936518771331058,
+      "grad_norm": 0.15612860023975372,
+      "learning_rate": 9.712302968428567e-08,
+      "loss": 0.3966,
+      "step": 343
+    },
+    {
+      "epoch": 0.9392491467576792,
+      "grad_norm": 0.15223388373851776,
+      "learning_rate": 8.888571658579704e-08,
+      "loss": 0.4062,
+      "step": 344
+    },
+    {
+      "epoch": 0.9419795221843004,
+      "grad_norm": 0.14373274147510529,
+      "learning_rate": 8.101024213241826e-08,
+      "loss": 0.3852,
+      "step": 345
+    },
+    {
+      "epoch": 0.9447098976109215,
+      "grad_norm": 0.15138757228851318,
+      "learning_rate": 7.349718656945504e-08,
+      "loss": 0.4184,
+      "step": 346
+    },
+    {
+      "epoch": 0.9474402730375426,
+      "grad_norm": 0.15817248821258545,
+      "learning_rate": 6.634710344009255e-08,
+      "loss": 0.4002,
+      "step": 347
+    },
+    {
+      "epoch": 0.9501706484641638,
+      "grad_norm": 0.16070495545864105,
+      "learning_rate": 5.9560519544614725e-08,
+      "loss": 0.4049,
+      "step": 348
+    },
+    {
+      "epoch": 0.952901023890785,
+      "grad_norm": 0.150055393576622,
+      "learning_rate": 5.3137934901585364e-08,
+      "loss": 0.4095,
+      "step": 349
+    },
+    {
+      "epoch": 0.9556313993174061,
+      "grad_norm": 0.15442615747451782,
+      "learning_rate": 4.7079822711015296e-08,
+      "loss": 0.4147,
+      "step": 350
+    },
+    {
+      "epoch": 0.9583617747440273,
+      "grad_norm": 0.15559975802898407,
+      "learning_rate": 4.138662931949255e-08,
+      "loss": 0.4086,
+      "step": 351
+    },
+    {
+      "epoch": 0.9610921501706484,
+      "grad_norm": 0.16370904445648193,
+      "learning_rate": 3.605877418729975e-08,
+      "loss": 0.4149,
+      "step": 352
+    },
+    {
+      "epoch": 0.9638225255972697,
+      "grad_norm": 0.15014031529426575,
+      "learning_rate": 3.1096649857508264e-08,
+      "loss": 0.4141,
+      "step": 353
+    },
+    {
+      "epoch": 0.9665529010238908,
+      "grad_norm": 0.15737587213516235,
+      "learning_rate": 2.6500621927054716e-08,
+      "loss": 0.4143,
+      "step": 354
+    },
+    {
+      "epoch": 0.9692832764505119,
+      "grad_norm": 0.15057510137557983,
+      "learning_rate": 2.227102901980971e-08,
+      "loss": 0.3928,
+      "step": 355
+    },
+    {
+      "epoch": 0.9720136518771331,
+      "grad_norm": 0.15434685349464417,
+      "learning_rate": 1.840818276162226e-08,
+      "loss": 0.4178,
+      "step": 356
+    },
+    {
+      "epoch": 0.9747440273037543,
+      "grad_norm": 0.14688508212566376,
+      "learning_rate": 1.4912367757366485e-08,
+      "loss": 0.4003,
+      "step": 357
+    },
+    {
+      "epoch": 0.9774744027303754,
+      "grad_norm": 0.1523001343011856,
+      "learning_rate": 1.1783841569968368e-08,
+      "loss": 0.4066,
+      "step": 358
+    },
+    {
+      "epoch": 0.9802047781569966,
+      "grad_norm": 0.1558927595615387,
+      "learning_rate": 9.022834701429839e-09,
+      "loss": 0.4023,
+      "step": 359
+    },
+    {
+      "epoch": 0.9829351535836177,
+      "grad_norm": 0.15682734549045563,
+      "learning_rate": 6.629550575847355e-09,
+      "loss": 0.4203,
+      "step": 360
+    },
+    {
+      "epoch": 0.985665529010239,
+      "grad_norm": 0.14982886612415314,
+      "learning_rate": 4.6041655244233315e-09,
+      "loss": 0.3923,
+      "step": 361
+    },
+    {
+      "epoch": 0.9883959044368601,
+      "grad_norm": 0.2183847725391388,
+      "learning_rate": 2.9468287724737642e-09,
+      "loss": 0.4022,
+      "step": 362
+    },
+    {
+      "epoch": 0.9911262798634812,
+      "grad_norm": 0.15420758724212646,
+      "learning_rate": 1.657662428434792e-09,
+      "loss": 0.4081,
+      "step": 363
+    },
+    {
+      "epoch": 0.9938566552901024,
+      "grad_norm": 0.1494101881980896,
+      "learning_rate": 7.36761474865455e-10,
+      "loss": 0.4013,
+      "step": 364
+    },
+    {
+      "epoch": 0.9965870307167235,
+      "grad_norm": 0.14783267676830292,
+      "learning_rate": 1.8419376145051294e-10,
+      "loss": 0.4018,
+      "step": 365
+    },
+    {
+      "epoch": 0.9993174061433447,
+      "grad_norm": 0.1596495360136032,
+      "learning_rate": 0.0,
+      "loss": 0.4225,
+      "step": 366
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 366,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.031005528979145e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-366/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2894cbb412e8163f51ee66bc37edad64bb67e6527266f7add94fd1e6f4dbcfc6
+size 6968

runs/Mar09_20-03-29_notebook-7f74bd20-6513-4a53-9281-c69f52e88ff1/events.out.tfevents.1741521880.notebook-7f74bd20-6513-4a53-9281-c69f52e88ff1.112856.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c963f0910a0222d05f352406d39dbf7375ac1e4bed1806434c1cfd621b42a645
+size 82717

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{%- if messages|length == 1 and messages[0]['role'] == 'assistant' -%}{%- if messages[0]['content'] is not none -%}{{'<｜Assistant｜>' + messages[0]['content'] + '<｜end▁of▁sentence｜>'}}{%- endif -%}{%- else -%}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{{'<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor -%}{%- endif -%}{% if add_generation_prompt %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2894cbb412e8163f51ee66bc37edad64bb67e6527266f7add94fd1e6f4dbcfc6
+size 6968